Search Results

The image recognition technology that is transforming the automation world Synthetic Computer Vision (SCV) is a groundbreaking approach to image recognition. It is a form of Computer Vision. Computer Vision is a type of software that enables computers to derive meaningful information from digital images, videos, and other visual inputs. In traditional Computer Vision, the most widely used version of the technology, an algorithm is trained to detect real world objects using hundreds and thousands of real images of those objects. Sourcing and preparing this high-quality training data is extremely costly and time-consuming. Therefore, the process it is not feasible to adapt and scale traditional Computer Vision to the demands of the masses. It is therefore unrealistic for most companies to consider its use for domain-specific applications. Synthetic Computer Vision is not burdened by this unnecessary barrier to adoption i.e. access to the necessary training data. This is because Synthetic Computer Vision does not rely on real data to train its algorithms. Instead, Synthetic Computer Vision is powered by Synthetic Data, a virtual recreation of the real world data that is used to train Computer Vision models to detect real world objects. For real world object detection, Synthetic Data encompasses rendered images and videos of a 3D, digital twin of a real world object including virtual scenes that it is placed in. This data represents the attributes of the object as well as possible environments in which it may be found in real life. It is used to train Computer Vision models to detect that real world object. Using Synthetic Data in this way, to train Computer Vision models, is the essence of Synthetic Computer Vision. Its use is leading to the widespread adoption, accessibility, and scalability of CV technology in ways that traditional CV with real data never could. SCV simplifies the input stage of image recognition. Instead of manually collecting and labelling thousands of individual data points for one object, you create a computer generated object and scenery that you can generate vast amounts of images with to train a CV model. Synthetic Computer Vision provides multi-modal metadata (2D/3D bounding boxes, depth data, masks, etc.) at virtually zero cost. With SCV, bounding boxes are created programmatically from the get go vs the long learning curve associated with traditional Computer Vision. SCV is extremely robust as it eliminates the human annotation errors that are typical with conventional CV methods. It is also extremely flexible as it captures real data variation with an easy to manipulate digital, 3D object as the training data. Synthetic Data not only benefits the initial stages of a CV workflow, it streamlines the entire CV process. Synthetic Computer Vision excels where conventional solutions are limited in many ways: Adaptability: The virtual nature of Synthetic Data makes it easy to transfer datasets and models between domains and CV use cases. Speed: A real-world deployment can be implemented in less than one week, saving you a ton of time and radically cutting costs. Scale: Easy access to image recognition datasets for over 100,000 SKUs through Neurolabs’ ZIA product. Quality: Achieve 95% accuracy for SKU-level product recognition from day one. For retailers and Consumer Packaged Goods (CPG) brands, Synthetic Computer Vision enables the automation of visual-based processes such as Shelf Monitoring or Shelf Auditing in real-world retail environments using virtual versions of Fast Moving Consumer Goods (FMCG). The most innovative supermarkets are already reaping the rewards of Synthetic Computer Vision by using ZIA (Zero Image Annotations) by Neurolabs to optimise On-Shelf Availability and put an end to Out-Of-Stocks for good. At Neurolabs, we are revolutionising in-store retail performance with our advanced image recognition technology, ZIA. Our cutting-edge technology enables retailers, field marketing agencies and CPG brands to optimise store execution, enhance the customer experience, and boost revenue as we build the most comprehensive 3D asset library for product recognition in the CPG industry.

Synthetic Data is the key to unlocking the automation potential of Computer Vision. Synthetic Data is a virtual recreation of real world data. It can be used to train Synthetic Computer Vision (SCV) models to detect real world objects. In traditional Computer Vision (CV), the most widely used version of the technology, an algorithm is trained to detect real-world objects using hundreds and thousands of real images of those objects. As you can imagine, sourcing and preparing this high-quality training data is extremely costly and time-consuming. The data gathering process makes it infeasible to adapt and scale the benefits of traditional Computer Vision to the demands of the masses. It is, therefore, unrealistic for most companies to consider its use for domain-specific applications. To put it simply, the automation potential of Computer Vision and image recognition technology will remain out of reach for the majority of companies until the data problem is solved. Synthetic Data is the solution. Practically speaking, Synthetic Data encompasses rendered images and videos of a 3D, digital twin of a real world object and the virtual scenes that it is placed in. This data represents the attributes of the object as well as possible environments in which it may be found in real life. It is used to train Computer Vision models to detect that real world object in varied contexts. Using Synthetic Data in this way, to train Computer Vision models, is democratising access to Computer Vision technology. It is enabling the widespread adoption and scale of CV technology for automation in ways that traditional CV with real data never could. Synthetic Data not only benefits the initial stages of a CV workflow, it streamlines the entire CV process. Using Synthetic Data in this way allows you to build an SCV solution that excels where conventional solutions are limited in many ways: Adaptability: The virtual nature of Synthetic Data makes it easy to transfer datasets and models between domains and CV use cases. Speed: A real-world deployment can be implemented in less than one week, saving you a ton of time and radically cutting costs plus you can add SKUs in mere minutes! Scale: Streamline product catalogues across multiple retail locations with no onboarding. Quality: Achieve 96% accuracy for SKU-level product recognition from day 1. Accuracy: Consistently high product detection accuracy that doesn't deteriorate over time. Savings: Save significant costs and time with no need for real data collection and annotation. For Consumer Packaged Goods (CPG) brands, Synthetic Data enables the automation of visual-based processes such as Shelf Monitoring or Shelf Auditing in real-world retail environments. The most innovative retail solution providers are already experiencing the benefits of using Synthetic Data by deploying Synthetic Computer Vision technology like ZIA by Neurolabs to automate supermarket operations. At Neurolabs, we are revolutionising in-store retail performance with our advanced image recognition technology, ZIA. Our cutting-edge technology enables retailers, field marketing agencies and CPG brands to optimise store execution, enhance the customer experience, and boost revenue as we build the most comprehensive 3D asset library for product recognition in the CPG industry.

All your questions about our retail-first Computer Vision software answered. About Neurolabs Q. What does Neurolabs do? Neurolabs provides Synthetic Computer Vision (SCV) software to retailers and Consumer Packaged Goods (CPG) brands to enable them to automate visual-based, in-store processes such as On-Shelf Availability. Q. What problem does Neurolabs solve? Currently, Neurolabs is focused on retail. Our software helps retailers and CPG brands address any on-shelf issues that they may be having. It enables them to automate manual processes like shelf monitoring and shelf auditing, saving them time and money. Our Synthetic Computer Vision Approach Q. What is Synthetic Computer Vision? Synthetic Computer Vision (SCV) is a form of image recognition software. SCV uses Synthetic Data to train Computer Vision (CV) models to detect objects in images and videos. Learn more. Q. What is Synthetic Data? Synthetic Data is a virtual replica of real data that is used to train Computer Vision models. For Neurolabs, our Synthetic Data takes the form of virtual, 3D models of supermarket products. Learn more. Q. What imagery is needed to create these 3D models? Neurolabs can create a virtual, 3D model of any Fast Moving Consumer Good (FMCG) product using either the digital packaging of the product or using six images that have been taken of the product (top, bottom, front, back, left side, and right side). Q. What makes you different to other Computer Vision solutions? Most CV solutions on the market today rely on a process that requires massive amounts of costly and time-consuming, real data as input. This makes it impossible to adapt and scale to the demands of the masses, and unrealistic for most companies to consider its use for domain-specific applications. Using Synthetic Data to train Computer Vision i.e. Synthetic Computer Vision makes the technology considerably more flexible, accessible, and scalable. Check out this post for a comparison of traditional Computer Vision and Synthetic Computer Vision. Real-Time Shelf Monitoring Q. How do you monitor the real retail environment once your solution is deployed? We can access images from the real retail environment using fixed cameras that are FTP-enabled. A photograph is taken at pre-defined intervals using these cameras. These images are then sent to the Neurolabs API for detections to be carried out. The detection data is made instantly available to our customers for the purposes of reporting and automation. We can also access these images via mobile devices or mobile applications. Simply capture an image of the retail environment and send the images to the to the Neurolabs API for detections to be carried out similar to the above. Synthetic Computer Vision allows us to deploy on mobile devices without making a tradeoff in terms of accuracy. Q. What kind of camera setup is required for fixed shelf monitoring? We recommend a resolution between 2k — 4k but can work with lower resolution models. Once the camera has a clear view of the shelf or fridge that you wish to be monitored, we can collect the imagery that we need. Q. After I install a camera, who maintains it? It is either the end customer or the System Integrator (SI) working with the customer responsible for the maintenance of the solution. Q. How do your models detect products that are at the back of the shelf?As long as there’s a glimpse of the SKU in the camera view, the technology will be able to detect it. A good test is the following: if you can tell with your eyes that there’s a product in the image, our technology should pick it up too. Q. What happens when the camera is obstructed by a person or an object? We have pre-built automated processes in place to continually check for such situations. In the case of a person being detected in the image, we instantly discard the photo and never store it. This is in line with privacy laws. That’s why we set the camera to take photos at very frequent time intervals (e.g. every 30 seconds). For the situation when an object is obstructing the camera, we alert the designated staff representatives to resolve the issue. Q. What happens when a product changes packaging? The fact that 23% of all Stock-Keeping Unit (SKU) packaging changes quarterly, makes this a very important question. Our solution is designed to adapt to SKU changes with no downtime. This is possible due to our Synthetic Computer Vision approach. We source the SKU’s packaging straight from the brand, allowing us to prepare the computer vision detection algorithms ahead of time in the event of any packaging changes. Q. How fast can Neurolabs deploy a working solution? We can implement a real-world deployment for you in less than one week. Q. What level of accuracy can Neurolabs achieve with Synthetic Computer Vision? We can achieve 96% accuracy for SKU-level product recognition from day 1. This increases further as the model carries out detections. Q. Once the system is installed, how can I use the data? The solution is very flexible in terms of deliverables. For example, the solution can be designed to send product availability insights straight into your Business Information (BI) tool for visualisation. The same insights can be fed into your internal systems (e.g. ERP) to enhance other processes (e.g. demand forecasting). End of day SKU-level reports can be set up to be sent to specific store representatives’ inboxes. Most importantly, live notifications and alerts can be sent to the designated store staff. All data (images and shelf insights) are saved and readily available for visual checks, when needed, through our platform. Q. What are the types of products you have difficulties recognising? Human sight provides the best proxy to assess the difficulty of product recognition. Compact objects (e.g. canned food, boxes) are easy to detect. On the other hand, transparent, reflective packaging might prove more challenging to deal with depending on environmental conditions such as lighting. However, the fact that Synthetic Computer Vision uses Synthetic Data makes these edge cases a lot less likely to cause an issue. Given the virtual nature of our Synthetic Data, we can simulate conditions that would typically make detection more difficult and train our models to detect the products even under those conditions. Q. Can you detect differences between the same products but in different sizes (e.g. small vs. large products)? Size is one of the characteristics that the our SKU detection models “learn” about the physical products. As long as your eyes can tell the difference between the products, the model will be able to do so too. Q. Do you provide a dashboard to visualise the status of the shelf? We integrate your product availability insights into straight into your Business Information (BI) tool of choice for visualisation. Q. How much time does it take to run the detection? Is it usable in real-time? Inference time is highly dependent on the computational power available. We see the inference time as a variable to be optimised based on the business use-case and the business needs. Real-time inference can be easily achieved with the online solution. Q. How much assistance do you need from store managers/store employees? Store managers and store employees are the ones that make use of the insights provided by the solution. We designed the solution so that it requires no assistance from their side and so that they can prioritise acting on the insights instead e.g. restocking a product that is Out-Of-Stock. Q. How can I get support? Is there a specific person? When can I reach you? We usually scale deployments through our technical implementation partners, therefore, they would be the primary point of contact for support. However, while working with us, there’s always a dedicated person available from our side to ensure the solution meets your needs and expectations. Q. Can I integrate this with my own internal systems? Absolutely. Our solution is designed from the bottom up to integrate with your existing systems. Integration flexibility and speed is one of the core distinguishing features of our solution. Q. Can I create alerts in your platform? Currently the platform and operational in-store actions are kept separately from each other. That’s in line with our goal to offer high user customisation when it comes to insights-driven actions. However, we integrate seamlessly with services that can trigger alerts and much more such as Robotic Process Automation (RPA) tools like UiPath. Q. Why do you have a platform? Can’t you just built the product detection model for me? The model is built for you automatically through the platform on the backend. We currently do not expose this step of the process as we want to make the experience as simple and user friendly for you as possible Q. Why do I have to deal with the 3D models? I already outsource product images. 3D models are critical to the scalability of the solution. Whereas product images are static data, 3D models allows us to reuse the same input data multiple times across different stores. It’s the only way to build a solution that scales across your hundreds or thousands of locations. Q. Are my 3D models shared with everyone else on the platform? It depends on our agreement. We are very flexible in terms of 3D asset ownership. We fully respect your privacy and, therefore, give you the choice. Of course, the more we can leverage existing 3D assets, the better the quality of the services we can provide and the lower the costs of the solution in the long term. Q. What kind of support / investments will be needed if we would like to go for PoC? During the PoC, we take care of the majority of the workload. However, we would need your help with the following: Business Case Definition Hardware & Network Configuration SKU On-Boarding In-store Contact Pricing Q. What is the price to use Neurolabs? For a Proof-of-Concept (PoC), we usually agree on a one-off price. Once in production, we have a pricing model based on the number of camera deployments (if it’s a fixed-camera solution) or the number of users (if it’s a mobile solution). Q. Why have you got a monthly fee? In retail, products and packaging change frequently. These changes require regular updating. We think a monthly fee best serves this. Q. Why can’t I pay for a company licence? To our knowledge, all enterprise software licences have some form of term, so after 3 years or so, a new licence is required. With the Neurolabs model, you get the benefit of being able to scale up or down as you need. Getting Started Costs Q. Why do you charge a Getting Started Fee? The simple answer is flexibility. Every client is different. However, all of our clients so far have wanted to implement with a combination of in-house, System Integration, and Neurolabs, with the project costs and hardware often coming from a different budget. Technology Privacy Q. What happens if peoples faces are in the stills Every picture is checked for Personally Identifiable Information (PII) before any insights are extracted from it. In case we detect any humans in the photo, the image is automatically deleted. Q. Where does the service run? We use all the major cloud providers and place the instance in a jurisdiction that you, the client, find acceptable. Q. How do you enforce GDPR regulations? Each image captured by a store camera is automatically verified for the presence of human content (customers or employees of the store) once it is stored in the cloud. If people are positively detected, the image is automatically deleted. The solution only processes images with no human content, therefore preventing any PII data being exposed during the process. In addition, our use of synthetically generated data to train the algorithms reduces the need for large image datasets collected in the store, thus decreasing the risk of PII exposure further. Security Q. How do you ensure the solution is secure? We use all the major cloud providers, so we rely on their processes and procedures to maintain and update operating systems. All data at rest is encrypted. All user interfaces are secured via username/password. Thus, we can interface with many of the single sign-on models available. APIs — We use OAuth to grant access to our APIs. Cameras Q. Can we use our cameras? The simple answer is, it depends. We have several models, but ideally, we need a resolution of 2K to take “stills” rather than a continuous feed. The key requirement, of course, is that the camera is pointed at the shelf. Our ideal camera is Power Over Ethernet (PoE) enabled with the ability to take one 4K still per minute as a minimum requirement. Cloud Q. We use a specific cloud services provider. Can we continue to use it with Neurolabs? We use all the major cloud providers, Amazon, Azure, and Google. Connectivity Q. Can you deploy the solution offline? We currently support online deployments only. With the increasing transition to cloud services in the grocery space, we are following the trend and prioritising online deployments. However, we do have plans to make our solution available offline in the future. Q. How do you connect the store to your service The solution needs reliable connectivity to the internet. This is usually achieved by connecting directly to the store router/switch. The bandwidth needed is minimal since we are working with still images as opposed to video stream. Commercial Risk Intellectual Property Q. Who owns the 3D Models? If you, the client, provide the complete model and skins, you own it. We would ask for an unlimited licence to use. If we create the model, then Neurolabs owns the model. If you stop using Neurolabs, we would provide access for a fee. Q. Who owns the Algorithms? Trained Computer Vision algorithms are not transferable. Q. Who owns the Digital Imagery? If you, the client, own the digital imagery, you continue to own it. You provide Neurolabs with a no-cost licence to use. Working With Neurolabs Q. How Can You Install Hundreds of Cameras A typical project has 3 parties: you, the client, ourselves as the solution owner and an integrator. The integrator can be your own in-house team, an integrator you already work with or one we can recommend. Our objective is to make it as straightforward and as low risk as possible. We have successfully done all three options. Q. Who have you worked with successfully in the past? In terms of end customers, we have worked with Tier 1 supermarkets in Europe such as Auchan and Uvesco Group. As implementation partners, we are working with medium-sized regional Solution Providers (Xabet) as well as worldwide Solution Providers such as ITAB and StrongPoint. Q. What happens to our model and data if you go out of business You can export your data. The model is not portable. You would need to use your data to train another Computer Vision algorithm. Q. Why don’t you do an end-to-end solution? Our solution has everything one needs to optimise On-Shelf Availability. All of our clients have looked for the flexibility that our API and Synthetic Data approach provides. Our platform seamlessly integrates with your existing technology, easily connecting to your supply chain and in-store systems. Our output formats are easily consumed by reporting systems such as Tableau and other downstream systems. Our event systems are easily integrated into your help-desk systems. Q. Who maintains the system once we get up and running? It can be either your internal IT/automation team, your System Integrator, or your Solution Provider partner. Neurolabs is fully responsible for the technological side of the solution, while working alongside other parties to ensure smooth implementation and maintenance of the solution. Competition Q. What makes Neurolabs better than existing OSA solutions that are on the market? Current shelf monitoring solutions just tell you about the problem, which is not enough. Our solution goes further in getting to the root cause of the problem, allowing you to address the cause not the symptoms (i.e. the Out-Of-Shelf or Out-Of-Stock). We use Synthetic Data and create digital twins of each of your SKUs to implement (and scale) faster and at a drastically reduced cost compared to using real data. We have access to the world’s largest digital SKU repository and have a process in place to deal with any new additions to the market. This is truly unique and currently the only scalable way of operating an effective Computer Vision solution in a space as dynamic and complex as retail. Q. How do you compare to just using existing store staff for improving OSA? Our solution is the equivalent of your store staff standing still in front of each shelf in your store 24/7 while reacting instantly to any anomalies spotted on the shelf, first by noticing the problem, then finding the root cause of it, before coming up with the right action to be taken and communicating that action to the right person. That’s without any decrease in monitoring and reporting accuracy due to inevitable fatigue or human error. Our solution allows you to move away from proxy sources and find a better way to track on-shelf reality. Providing 24/7 shelf truth data, the solution helps you get smarter and more productive at delivering human based interventions to reduce OOS, reduces the complexity of retail, and improves the accuracy of forecasting for increased OSA. Return On Investment Q. How can you guarantee a return on our investment? We cannot. However, we have built a robust business case with very conservative assumptions and worst-case costs, and in all our scenarios, the calculations show a positive return. We would very much like to show you our model and get your feedback. Chat to our Sales team today, or reach out to hello@neurolabs.ai to learn more! Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. Neurolabs helps optimise in-store retail execution for supermarkets and CPG brands using a powerful combination of Computer Vision and Synthetic Data, called Synthetic Computer Vision, improving customer experience and increasing revenue.

Real Data vs Synthetic Data The Image Recognition Status Quo Computer Vision (CV) has come along way in the past few decades. From self-driving cars to Optical Character Recognition (OCR), it continues to transform the world around us. Deriving meaningful information from digital images unlocks limitless automation potential. Yet, for a field of study which has grasped the attention of AI researchers since the 1960s, mainstream breakthroughs in Computer Vision have not been as drastic as the lofty advances that were promised. The true potential of Computer Vision, as it stands, is only accessible to a niche of image recognition experts and machine learning specialists worldwide. While the Teslas and Googles of the world can spend eye-watering budgets on their AI endeavours to develop next-level consumer products, there exists a large majority of non-technical industries, ripe for automation with the technology, that are hindered by an unnecessary barrier to adoption, data. Attempts to democratise Computer Vision for widespread commercial use have been throttled by failure time and time again to optimise its largest dependency, the sourcing and preparation of high-quality training data. Most CV solutions on the market today rely on a process that requires massive amounts of costly and time-consuming, real data as input. This makes it impossible to adapt and scale to the demands of the masses, and unrealistic for most companies to consider its use for domain-specific applications. Simply put, traditional Computer Vision and image recognition technology will remain out of reach for the majority of companies until the data problem is solved. The Devil is in the Data Currently, it is estimated that only 1% of AI research is focused on the sourcing and preparation of data for AI models. The other 99% is focused on AI model training and algorithm optimisation. This is in spite of the fact that the data preparation stage of traditional Computer Vision, which requires vasts amounts of real data, takes up largely 80% of a developer’s time while 20% of their time is spent on training the model itself. This disconnect between where a developer spends their time versus where advances are being made presents a very big problem for the future of Computer Vision. On the flip side, it presents a very big opportunity for those who are willing to innovate with a more sophisticated and capable approach. Rather than approaching the problem with both hands tied behind your back i.e. having a human painstakingly collect and label copious amounts of real data to train a Computer Vision model, take a step into the virtual world to generate that training data synthetically and experience a CV process that is faster, more cost-effective, and truly scalable. Breaking the Mold Synthetic Computer Vision is a groundbreaking approach to image recognition that is powered by Synthetic Data. Synthetic Data is a virtual recreation of real world data that is used to train Synthetic Computer Vision models to detect real world objects. For real world object detection, Synthetic Data encompasses rendered images and videos of a 3D, digital twin of a real world object including virtual scenes that it is placed in. This data represents the attributes of the object as well as possible environments in which it may be found in real life. It is used to train Computer Vision models to detect that real world object. Using Synthetic Data to train Computer Vision models is known as Synthetic Computer Vision (SCV). Its use is leading to the widespread adoption, accessibility, and scalability of CV technology in ways that traditional CV with real data never could. SCV simplifies the input stage of image recognition. Instead of manually collecting and labelling thousands of individual data points for one object, you create a computer generated object and scenery that you can generate vast amounts of images with to train a CV model. Synthetic Computer Vision provides multimodal metadata (2D/3D bounding boxes, depth data, masks, etc.) at virtually zero cost. With SCV, bounding boxes are created programmatically from the get-go vs the long learning curve associated with traditional Computer Vision. SCV is extremely robust as it eliminates the human annotation errors that are typical with conventional CV methods. It is also extremely flexible as it captures real data variation with an easy to manipulate digital, 3D object as the training data. Synthetic Data not only benefits the initial stages of a CV workflow, it streamlines the entire CV process. Synthetic Computer Vision in Action 1. Digital Twins SCV always starts with high quality data. Step one is to create a digital twin of the real world object. Take, for example, a supermarket product or Stock-Keeping Unit (SKU). In order to generate Synthetic Data for a product, we first create its virtual doppelgänger using its real world packaging in 3D modelling software. Using Neurolabs, we can upload the digital twin of the product to the platform to be used along with thousands of other products to train a Computer Vision model for our chosen CV use case. With a digital twin in hand, we can use it to create a Synthetic Dataset. 2. Synthetic Datasets Using the same software that we used to create the virtual, 3D version of the product, we build virtual scenes or digital replicas of real world environments in which the object can be placed. This helps create environmental context for the training stage. Once we have our digital twin and virtual scenes, we can render as many images and videos, with infinite variations of the products and their environment, as we want. A collection of these rendered images and videos makes up the Synthetic Dataset which will be used to train the Computer Vision model. As we are working with Synthetic Data, we aren’t limited by the data collection constraints of reality. We can simulate any position or condition for the product using its digital twin. We can also simulate whatever background we want using variations of the virtual scenes. In essence, the form and quantity of data is limitless. There are three specialised techniques that the Neurolabs platform provides to generate Synthetic Datasets: Using Domain Randomisation, Using Pre-Existing Scenes, Using own scenes sourced from the 3D modelling software of your choice. Machine Learning algorithms will create a diverse mix of data for the Synthetic Dataset automatically, cutting even more time from the process. 3. Model Training Armed with a Synthetic Dataset, you can now use it as the training data to train a Computer Vision model to detect real products in the real world. For example, you could use a Synthetic Dataset containing digital versions of supermarket products to help train a CV model to carry out Shelf Monitoring or Shelf Auditing in very different, real-world retail environments. Using Neurolabs product, the training process is automated and easy to test on platform. Training a precise Computer Vision model is seamless with Synthetic Data. Real World Deployment The result is a fully trained Synthetic Computer Vision model that is as simple to deploy to a real world, production environment as making a call to an API endpoint. Neurolabs makes the whole process simple by providing all of the data generation and SCV model training via our platform. The product then applies an iterative training process to improve the synthetic training data using the models themselves. Using Synthetic Data in this way allows you to build an SCV solution that excels where conventional solutions are limited in many ways: Adaptability: The virtual nature of Synthetic Data makes it easy to transfer datasets and models between domains and CV use cases. Speed: A real-world deployment can be implemented in less than one week, saving you a ton of time and radically cutting costs. Scale: Easy access to image recognition datasets for over 100,000 SKUs through Neurolabs’ ReShelf product. Quality: Achieve 96% accuracy for SKU-level product recognition from day 1. Using Synthetic Data, a Synthetic Computer Vision model can be deployed at speed to detect any real world object such as grocery store products. Data Duel: Comparing the Use of Real Data versus Synthetic Data Neurolabs has been deploying Synthetic Computer Vision models in the real world for two years now. Our Machine Learning experts pitted a Computer Vision model trained using real data against one that was trained using Synthetic Data. Specifically the test focused on the task of object localisation. Real Data For the real data, SKU110K, an open source dataset of mobile images from supermarkets, released in 2019 by Trax, was used. They benchmarked the performance of a pre-trained model on the SKU110K dataset. This real dataset contains more than 10,000 manually acquired images. The estimated cost of collating this real dataset is about $20,000. A mAP (Mean Average Precision) of 60% mAP was reached when tested on a new real dataset from a real world grocery store. Synthetic Data After generating 1,000 Synthetic images using Neurolabs’ Synthetic Data generator, the team observed a mAP of 65% as tested on the real data from the real world supermarket. The team randomised the lighting, camera locations and position of the objects. They used physical simulations to create more realistic structure when creating the datasets. When compared with the real data results, they observed a 5% increase in mAP using Synthetic Data. This resulted in a 100x decrease in cost and time associated with the deployment, thus making the solution much more scalable. Conclusion Using Synthetic Data proved to be the superior option when deploying Computer Vision in a real world environment. Not only did the mAP improve but the cost and time involved in the project was radically reduced. Furthermore, applying Neurolabs’ data mixing and domain adaptation techniques increases the model’s mAP performance to 80%. This was done using a mix of Synthetic and real data at a ratio of 100:1 i.e. using 1,000 synthetic images with 10 real annotated real images. A Virtual Future Commercial application of Computer Vision will continue to grow in the coming years. The smart use of the technology will become a necessity for any company that wishes to effectively automate visual-based tasks. The most forward thinking companies understand the value of investing in the right image recognition tech stack. Innovating in this area will not only create organisational-wide process efficiencies but indeed create a competitive advantage for the organisations that deploy it. Synthetic Data is the future for a truly scalable and easily deployable Computer Vision solution. Synthetic Computer Vision democratises automation potential that should not be reserved for an elite technical few but instead should be readily available to the masses to positively impact the world. Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. Neurolabs helps optimise in-store retail execution for supermarkets and CPG brands using a powerful combination of Computer Vision and Synthetic Data, called Synthetic Computer Vision, improving customer experience and increasing revenue.

UK-based Synthetic Computer Vision startup Neurolabs aims to democratise computer vision by packing it into a readily available, out-of-the-box solution for companies that do not belong to the tech elite, who lack access to data and struggle with budgets. Computer Vision (machines that teach themselves to see and recognise everyday objects) companies have made waves with some well-funded series A and series B rounds. Early rounds of $50M were a rare sight in the space - although investors are excited to fund anything with Artificial Intelligence, the hand that could reliably and efficiently feed AI the quality visual data that it requires has been largely overlooked until recently. Fear of change and complacency has been comfortably attributed to old industries like physical retail for not being decisive enough to jump on AI automation. But it’s not even half of the story. In fact, global Artificial Intelligence in retail is expected to soar from last year’s $4.84 billion to $31.18 billion in 2028. There are other barriers to overcome. Synthetic Data’s superiority over real-life data in terms of accuracy, speed, cost, and legal compliance has been well established. Synthetically generated data will completely overtake real-life data by 2030, according to Gartner. But unstructured visual data for AI processes in retail needs very precise and anticipating 3D-modeling of everyday physical objects like milk cartons and cereal boxes. For a machine to simply recognise an object on the shelf is not enough. To anticipate and reproduce real-life changes in packaging and design is the real feat for Synthetic Computer Vision championed by Neurolabs. “Generating synthetic data doesn’t automatically translate into working Computer Vision algorithms. It’s a learning process in itself and we have been perfecting it for more than 2 years now.” affirms CEO and Founder Paul Pop. Then there’s the talent shortage: while data is rapidly being commoditised, businesses in traditional industries have been struggling to execute on automation initiatives due to the scarcity of Computer Vision engineers. To the rescue comes Neurolabs’ out-of-the-box solution that enables software engineers and citizen developers to build computer vision solutions as easily as building a website. Unlike the industry incumbents like Nvidia and Unity, the startup wagers on no-code and low-code implementation. The technology reduces Computer Vision model development costs, and time to deployment to literal days instead of months. With such a breakthrough in accessibility, is it correct to imagine every single physical product on the shelf anywhere in the world being fully digitised? “We are amassing the largest 3D product repository in retail, aiming to reach over 100,000 products this year. The sky's the limit: a streamlined process of adding any existing product to our database in minutes is in place,” continues Pop. Building virtual twins of real-world products on a mass scale unlocks the potential for Synthetic Computer Vision to be applied at each stage of the consumer packaged goods lifecycle, from manufacturing and distribution, to in-store, e-commerce, and recycling. Based in Edinburgh, UK, with offices in London & Cluj, Romania, the Synthetic Computer Vision company has made big strides in the last 18 months, landing the French discounter Auchan as a client, with other big brands in the pipeline. Led by Southeastern Europe specialist fund LAUNCHub Ventures, the $3.5 million seed round attracted Berlin’s Lunar Ventures, Techstart and London’s 7% Ventures as co-investors. “It’s obvious that synthetic data is the most efficient way to train your algorithms and quickly develop computer vision applications,” said Stan Sirakov, General Partner at LAUNCHub Ventures in a statement following the funding round. “The Neurolabs team has proven a strong edge in object detection in different industry applications.” ‘While the Teslas and Googles of this world can pour into their AI operations their unmatched financial and human resources to develop next-stage consumer products like self-driving cars, there are a plethora of non-tech industries that are ripe for the latest automation technologies but struggle with adoption,'' added Sirakov. “With an end-to-end solution so easy to implement, we see it as a way to democratise Computer Vision.” Neurolabs plans to use the new capital to scale operations and expand its offering into several consumer packaged goods use cases. About LAUNCHub LAUNCHub Ventures is a leading early-stage venture capital fund, investing in technology startups in the Seed and Series A funding stages. We invest in Central and Southeastern Europe (SEE & CEE), and in companies built by ambitious founders from that region who are based in the leading startup hubs such as London, San Francisco, and beyond. For more information, please visit www.launchub.com. About Lunar Ventures Investing in early stage European DeepTech Software. We are technical investors partnering with technical founders who are building at the intersection of DeepTech and software. Our mission is to help you turn your sci-fi ideas into working products. For more information, please visit www.lunar.vc About Techstart Ventures Techstart Ventures is a leading investor of seed capital across Scotland and Northern Ireland and recently won ‘Investor of the Year’ at Turing Fest’s 2019 Scottish Tech Startup Awards. Techstart Ventures LLP manages the Scottish Growth Scheme – Techstart Ventures Equity Finance LP Fund - which has been financed by support from the Scottish Government and the European Regional Development Fund from the 2014-20 European Structural Funds Programme. For more information, please visit www.techstart.vc About 7percent 7percent Ventures invests in early stage startups run by founders with moonshot ambitions. All partners are ex-founders turned investors. Past investments include OculusVR (sold to Facebook), Blue Vision Labs (Lyft) and Magic Pony Technologies (Twitter). 7percent believes the founder is their customer, offering advice from first hand experience and support from a curated network of over 150 advisor investors. For more information, please visit www.7pc.vc Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. Neurolabs helps optimise in-store retail execution for supermarkets and CPG brands using a powerful combination of Computer Vision and Synthetic Data, called Synthetic Computer Vision, improving customer experience and increasing revenue.

Using virtual products to solve real-world problems Customers Come First The international ITAB Group is a leading supplier of high-quality retail store solutions such as cash desks, self-checkout, and customer guidance systems. They design, manufacture, deliver, and install retail solutions from end to end using the most innovative technologies available. Their primary aim is to offer each customer a first-class service and their highest priority is always customer satisfaction. This is no easy feat when you consider the rapidly changing demands of the modern consumer combined with constantly increasing competition amongst Fast Moving Consumer Goods (FMCG) brands. To ensure that they can continue to maintain such stellar levels of service and keep their retail customers happy at scale, they have implemented many automated solutions. One such system involves the use of image recognition technology to automate visual-based tasks for retailers. Specifically, they have experimented with Computer Vision (CV) to streamline the processes involved in shelf monitoring and inventory management in supermarkets and retail stores. As part of their experiments, they explored a new type of CV known as Synthetic Computer Vision (SCV) and sought to put the new technology’s capabilities to the test. Virtual Reality Synthetic Computer Vision (SCV) is an innovative, AI-powered approach to image recognition that enables the user to automate the detection of real world objects such as Fast Moving Consumer Goods. In order to detect an object in the real world, the technology is trained using a virtual replica of that object. Images and videos are obtained using this virtual replica, or 3D asset, that, when combined with rendered images and videos of the 3D asset places in 3D, virtual scenes, compose the Synthetic Data. In short, the Synthetic Data is a computer generated version of a supermarket shelf with products on it. By using Synthetic Data for CV, the technology radically reduces the cost and time traditionally required to train and deploy image recognition models. This makes the automation of visual-based tasks such as shelf monitoring in supermarkets so much simpler. ITAB take a diligent approach when it comes to choosing the right system for improving in-store experience for their customers. They are strategic when it comes to choosing a solution that will withstand the test of time and easily scale across many locations so exploring the use of SCV was a no-brainer. ITAB wanted to test the capabilities of Neurolabs’ SCV platform ZIA to see whether it could improve the performance of their existing CV models. These models would be used to automate in-store shelf monitoring. If successful, they aimed to switch to using fully Synthetic Datasets for future CV applications due to the time and cost saving provided by the use of Synthetic Data versus real data alone. Proof of Concept In order to prove that SCV would perform in a real world retail environment, ITAB set up a lab environment, consisting of multiple products on a supermarket shelf, to test it. The purpose of the project was twofold: To evaluate the effectiveness of the detection of Out-Of-Stock products using SCV To investigate the efficiency and scalability of using Synthetic Data versus real data to train CV models to detect products on supermarket shelves Focusing on a sample of 50 different Stock-Keeping Units (SKUs) across multiple categories, they set out to prove whether Synthetic Data could improve their workflows and, ultimately, benefit the end customer. The SCV Process 1. Digital Twins To get started, ITAB needed high quality training data. Instead of the traditional approach to CV of capturing and labelling vast amounts of real images, SCV simplifies the initial data requirement to just one virtual recreation of the object that is being detected. In this case, they needed virtual recreations of their supermarket products. Neurolabs ZIA created virtual versions of each of their SKUs using six images of each product. These images were used to build a virtual, 3D model for each SKU. The end result were 3D assets that were ready to be uploaded to ZIA as the input for the Synthetic Dataset generation stage. The platform automatically labelled each of the products in the process. 2. Synthetic Datasets Once the 3D asset was uploaded to Neurolabs platform, ZIA, various 3D virtual scenes were automatically generated and Synthetic Datasets, in the form of 2D images, were created, to represent the multiple ways that the product can appear in real life. These datasets are used as examples for the CV algorithms to learn how the product may look like in varying, different environments i.e. to train a CV model. For ITABs use case, the datasets contained variations of their virtual products in very different scenes to help train their CV model to carry out shelf monitoring in very different, real-world retail environments. There are three specialised techniques that Neurolabs offers to generate Synthetic Data on the platform: Using Domain Randomization, Using Pre-Existing Scenes, Using ITABs own scenes sourced from AutoCAD models of their customers’ stores. ITAB tested all the three methods to see which worked best for them. 3. Model Training Once the datasets were ready, ITAB used them to train a CV model on the Neurolabs platform, ZIA. They were able to rapidly deploy that same model to detect the supermarket products in the lab environment that they had created. Deploying advanced image recognition technology with ZIA is as simple as making an API call. Tried and True Once ITAB had deployed their SCV model and tested its ability to carry out automated shelf monitoring, they compared the performance of the model with one trained using real data and they were very pleasantly surprised by the results. They were also very impressed with the ease and speed of the SCV process and how seamless the Synthetic Dataset came together. They see it as a promising technology and are pushing for it to be deployed it in a real-world retail environment as soon as possible. By using Synthetic Computer Vision to automate in-store shelf monitoring, ITAB was able to build a CV solution that excelled where conventional solutions are limited in many ways: Speed: A real-world deployment can be implemented in less than one week. Scale: Access to image recognition datasets for over 100,000 SKUs through the ZIA platform. Quality: Achieve 95% accuracy for SKU-level product recognition from day 1 and increase to above 98% for specific categories.. The most innovative retail solution providers like ITAB, who embrace state-of-the-art image technology like SCV, are ensuring a future of many very happy customers for years and years to come. At Neurolabs, we are revolutionising in-store retail performance with our advanced image recognition technology, ZIA. Our cutting-edge technology enables retailers, field marketing agencies and CPG brands to optimise store execution, enhance the customer experience, and boost revenue as we build the most comprehensive 3D asset library for product recognition in the CPG industry.

A Truly Scalable Image Recognition Software for Fast Moving Consumer Goods Reality Check Automating the task of shelf auditing for Consumer Packaged Goods (CPG) and Fast Moving Consumer Goods (FMCG) across thousands of retail locations around the globe is a monumental task. Despite the best efforts of Field Force Management (FFM), even the most sophisticated mobile, automated solutions for in-store retail execution are limited by one key factor, the availability of high quality product data. The conventional approach has been to deploy image recognition techniques with traditional Computer Vision (CV). This involves the tedious collection and labelling of an eye-watering mass of real images of each Stock-Keeping Unit (SKU). These images are then used to train the software to detect the products that need to be detected. The time and cost required to reach a reliable real-world deployment of this technology should be sobering for any retail technologist that is serious about the cost-benefit of automation. The simple truth is that the most common form of image recognition deployed in retail today is extremely limited by the technology that underlies it. The good news is that a much better solution to the problem has emerged, one that is completely transforming the shape of CPG merchandising and the effectiveness of Field Force Management in retail. Virtual Perception Neurolabs has developed a novel approach to shelf monitoring for supermarkets, the benefits of which are easily transferrable to mobile shelf auditing via FFM. For the shelf monitoring solution, we use fixed, in-store cameras to collect SKU data in real time. That data is then analysed by our SKU-detection software to empower each store to optimise inventory and boost sales. The true game-changer here is the way in which our SKU-detection software is trained and deployed. Instead of relying on copious amounts of real data for each SKU, Neurolabs uses Synthetic Data in the form of virtual, 3D versions of each supermarket product. These 3D, digital recreations of each CPG product are used to train CV models in a much more efficient and scalable way. We call this technology Synthetic Computer Vision (SCV) and have been successfully deploying it for retailers in our technology which uses fixed cameras in retail environments. The great thing about using Synthetic Data is that it is extremely adaptable and the data from one use case such as shelf monitoring can easily be reused for many different ones. This is exactly what we have found from our real world deployments in supermarkets and retail stores. The advantages of Synthetic Computer Vision are entirely transferable to a mobile solution for use by Field Force Management in CPG shelf auditing Knowledge Transfer For shelf auditing, we started with the most important element first, the data. In one day we generated complete SKU and scene data for a fixed camera use case. These datasets were perfect for training our SCV models to detect CPG products. The ability to manipulate each SKU’s virtual model at will removes the need for collecting countless real images of each SKU in different environments and conditions. Instead, our AI technology enables the procedural generation of endless different variations of each virtual CPG product in order to train the SCV models to account for real world variability at a speed and scale that traditional CV simply cannot match. We were very happy with the detections for a fixed setup so we turned our attention to a different form of deployment, mobile. One of the most striking benefits of using Synthetic Data for Computer Vision is the ease of which the effort spent on one use case transfers to another. After the initial one day it took to generate Synthetic Data for fixed camera shelf auditing, we were pleasantly surprised that it only took three hours to develop a CPG product detector on a mobile device. Taking the conventional approach to Computer Vision would have made this timeline impossible. With Synthetic Data, we were able to execute and deploy at speed, testing and validating our assumptions of the mobile shelf auditing use case in a truly cost-efficient and scalable way. As a result, our new mobile product detection software which was purpose built with Field Force Management in mind, came to be. Using ReShelf Go as your SKU recognition software of choice for your FFM mobile app empowers your field agents to get the job done more effectively and provides your CPG clients with trustworthy, real-time information to compute their most important retail execution KPIs. Handheld Hero Using SCV we have achieved 96% accuracy for SKU-level product recognition as a baseline from day 1. Accuracy continues to improve as the SCV model carries out more detections. This level of precision, combined with the adaptability of the training data, is crucial for a successful automated shelf auditing deployment given the ever-changing nature of the retail environment and the inconsistency that comes from images captured on mobile devices. For FFM companies, a superior approach to image recognition, using a mobile device for data capture, can be tested in less than a week. This reduces the cost and risk associated with switching to a new technology as you can rapidly verify its effectiveness before considering implementing the software into your native mobile application. All of our datasets are available in the Neurolabs platform and deploying one of our custom-trained Synthetic Computer Vision models is as simple as making a call to our API endpoint. Any CPG product can be created in virtual reality to take SKU recognition to the next level. No longer held back by the limitations of traditional image recognition, using Synthetic Computer Vision, you can achieve unprecedented benefits such as: Speed: A real-world deployment can be implemented in less than one week. Scale: Access to image recognition datasets for over 100,000 SKUs through the ReShelf platform. Quality: Achieve 96% accuracy for SKU-level product recognition from day 1. With such vast improvements to your image recognition workflows, why not try it for yourself? Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. Neurolabs helps optimise in-store retail execution for FFM companies and CPG brands using a powerful combination of computer vision and synthetic data, improving customer experience and increasing revenue.

Using Synthetic Computer Vision to Optimise Mobile Shelf Auditing Automation in Sight The rapidly changing demands of the modern consumer combined with constantly increasing competition has made effective in-store execution more critical than ever for retailers and Consumer Packaged Goods (CPG)/Fast Moving Consumer Goods (FMCG) brands alike. For supermarkets, in-store execution requires the laborious effort of manually monitoring shelves by sight, as often as possible, with the human resources that are available to them. This is overly onerous, prone to human-error, and difficult to scale. For CPG brands, in-store execution can be carried out in collaboration with the retailer using the above approach but this is quite limiting and slows down the transfer of crucial operational information that is required to make optimum merchandising decisions at speed. More often than not, CPG brands employ thousands of field agents to visit the stores that stock their products and conduct shelf auditing on their behalf. This approach can lead to inconsistencies in data quality and result in very large overheads. Faced with similar challenges in both shelf monitoring and shelf auditing, retailers and CPG brands are turning to automation to streamline the process. Computer Vision (CV), in particular, is playing a crucial role in the successful deployment of these automated in-store solutions. Teaching a Computer to See Computer Vision is a speciality of Artificial Intelligence that trains a computer to interpret and understand visual data from the real world. It is the field of computer science responsible for image recognition. At its simplest, a series of algorithms break down the visual data of a product from an image and compare it against a database of confirmed images of that same product to determine how likely a match it is. With a successful match, the software can use this product detection data, in collaboration with other automation tools, to carry out a specific process such as informing in-store staff when a product’s on-shelf inventory is running low. As supermarkets and CPG brands turn to the lucrative automation promises of Computer Vision, the technology has had to undergo an evolution of sorts as the traditional approach struggles to meet the demands of modern retail. Limited Vision Most Computer Vision (CV) solutions on the market today rely on a process that requires massive amounts of costly real data that is unnecessarily time-consuming to collect as input to validate product detection. Consider the thousands of product lines and hundreds of thousands of individual SKUs that an algorithm must be programmed to recognise under so many different environmental conditions. The average modern supermarket is, of course, a dynamic, ever-changing place so any automated solution deployed in a store must be flexible enough to perform effectively. The sheer input data requirements makes traditional CV impossible to adapt and scale to the demands of even the average retailer. Simply put, conventional CV, the most widely used form of the technology on the market today, is not a feasible or scalable approach to the demands of modern retail execution. Luckily, a new form of CV is emerging that can handle the challenge. Unlimited Possibility Synthetic Computer Vision (SCV) is a new approach to image recognition that utilises synthetic or computer generated datasets in the training of computer vision models. In doing so, the technology is not limited by reliance on the laborious collection and labelling of huge amounts of real data to be able to detect an object. Neurolabs uses SCV in its technology which is purpose built to detect CPG products at the SKU-level. The synthetic data that Neurolabs uses to train its models comes in the form of 3D digital recreations of each CPG product. By providing a synthetic copy or 3D digital twin of a product as training data to a computer vision model, the necessity for collecting hundreds or thousands of real images of that individual product is removed, drastically reducing the time and cost involved in deploying the product detection technology in a real-world retail environment. ReShelf uses Artificial Intelligence to automatically create variations of a product’s synthetic copy as well as its environment to train itself to detect the product under variable conditions. Consider the many different ways that a single product could be displayed on a shelf, the condition of the packaging, and the specific retail environment as just some of the many variables that the SCV approach accounts for that makes the traditional approach to computer vision so infeasible. Using synthetic data as the training material for a computer vision model in this way means you have access to limitless image recognition applications. Endless CPG use cases are possible using the same 3D digital copy of a product from automation in manufacturing and distribution, to in-store inventory and checkout. A Fixed Position ReShelf is Neurolabs’ answer to the automation challenges retailers face with in-store shelf monitoring. By using Synthetic Computer Vision via fixed, in-store cameras, ReShelf excels where conventional solutions have been limited in many ways: Speed: A real-world deployment can be implemented in less than one week. Scale: Access to image recognition datasets for over 100,000 SKUs through the ReShelf platform. Quality: Achieve 96% accuracy for SKU-level product recognition from day 1. Retail innovators such as Auchan have already seen the impact of using SCV with a fixed-camera deployment for in-store shelf monitoring. For retailers, automated shelf monitoring solutions using Synthetic Computer Vision are proving to be the most scalable and impactful approach. Using a powerful combination of fixed, in-store cameras with the latest advancement in image recognition, supermarket chains such as Auchan and UVESCO have achieved complete visibility of their store shelves in real time. These benefits are not limited to fixed-camera setups. Neurolabs has taken the power of Synthetic Computer Vision and proven that it is transferable to a mobile use case. Using synthetic data, Neurolabs has made it possible for CPG brands to achieve similar success with shelf auditing on the go. Going Mobile Neurolabs is now providing the automation potential of Synthetic Computer Vision from a mobile device by transferring the lessons learned from fixed-camera shelf monitoring to the mobile shelf auditing use case. CPG brands can now streamline retail execution with access to SKU-level image recognition technology without the need for in-store fixed cameras. With real-time product detection available on the go, your field force are empowered with the right information at the right time to execute in-store brand strategy most effectively. Field agents simply upload shelf images from their mobiles devices to the Neurolabs API which will automatically stitch the images together to generate a complete scene for SKU-level detection. SKU-level analysis provides you with detailed information to compute your most important retail execution KPIs such as Out-Of-Shelf rate, shelf share percentage, competitor price comparison, and so much more. With complete visibility of your product in real time, you can quickly and easily tailor your merchandising strategy at the store level. Insights in Hand As the demands of a growing consumer base combined with ever-increasing competition continue to grow, CPG brands are faced with the daunting task of maintaining the best possible merchandising experience across many different markets and locations. Automation is critical to a successful and cost-effective in-store brand strategy and yet many CPG brands continue to rely on the manual intervention of their field agents to give them a complete picture of product performance from the shop floor. Using synthetic data with Computer Vision enables the speed, flexibility, and scalability needed to deploy an effective automated solution to retail execution. Achieving next-level retail activity optimisation and optimising your in-store retail execution strategy is now so much simpler with Neurolabs. Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. Neurolabs helps optimise in-store retail execution for supermarkets and CPG brands using a powerful combination of computer vision and synthetic data, improving customer experience and increasing revenue.

This guide details how to create an automated planogram compliance detector using the Neurolabs platform. You can also check out our video guide below. A quick demo of how the Neurolabs platform helps automate planogram compliance. Firstly, log in to Neurolabs at app.neurolabs.ai Once you’re logged in, click on “ReShelf” on the left hand side of the screen. ReShelf is our computer vision solution to automate planogram compliance and on-shelf availability management in supermarkets. On the ReShelf page, click the “Create” button. From here, enter a name for your Planogram in the “Name” field. Then, simply upload an image of the products on the display for which you want to create a Planogram for. You can now label and annotate each grouping of products to your liking. Firstly, select the option to “Replace the generic “object” label with specific labels of the products in your planogram”. Then, click and drag bounding boxes around each different product group like so. Now, enter the specific details for each product grouping. Be sure to select a product from the drop down list to annotate the bounding box correctly. You should do this for all of the products in the planogram image Once you’re happy, click “Upload”. Next, you want to create a ReShelf job to process any of the images that will be fed into to the Planogram compliance detector. To do this we click the “Manage ReShelf Jobs” option on the planogram we just created. From here click “Create a ReShelf job”. Choose a “Name” for your ReShelf job and select the type of “Product Detector” that will carry out detections for this planogram. For this example we will use a “Generic” object detector but this will vary depending on your specific use case. You can leave the “Matching Threshold” as its default value for now. Press “Save” to successfully create the ReShelf job. Under “Send Images”, you now have an endpoint that you can use to query and send images to. As you can see below we have the POST request, the endpoint, and the API key. We can now send any shelf images to this endpoint. The purpose of sending images here is to have our planogram compliance detector ensure that the products on the shelf in the image comply with our ideal planogram which we created earlier. The response to queries using this endpoint will be returned in the form of a JSON file which includes predictions in the form of the bounding boxes and product detection scores. It will also include information on whether or not the image queried matches the planogram that we originally created. This information will also reveal whether or not there is an out-of-stock. Thanks for checking out our guide. Be sure to check out our post on How to Enhance your Brand with Automated Planogram Compliance for more tips and useful information! Reach out to the Neurolabs team if you have any questions and we’ll be happy to help! 🙂 Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. Neurolabs helps puts an end to Out-Of-Stocks and automates Planogram Compliance using a powerful combination of computer vision and synthetic data, improving customer experience, enhancing brands, and increasing revenue. 🤖

Enhancing your Brand with Automated Planogram Compliance What’s at stake? Your brand’s reputation. Merchandising is most commonly described in the below terms: The presentation and promotion of goods that are available for purchase for both wholesale and retail sales. This includes marketing strategies, display design, and competitive pricing, including discounting. Merchandising is important for retailers looking to cultivate their brand, improve the experience of customers, compete with others in the sector, and ultimately, drive sales. When we bear in the mind this description, we realise that merchandising, and how a brand chooses to display its merchandise, is very much integral to the heart of that brand. Be it a Consumer Packaged Good (CPG) brand or the brand of retailer that physically displays the product, brand reputation is on the line whenever and however a product is displayed to a customer. The supermarket shelf is rife with competition. Consumers notice less than 40% of the products in a specific category and spend less than 15 seconds in front of any given shelf [1]. The good news is that only 30% of all purchasing decisions are fixed before entering a store meaning the possibility of influencing customer buying behaviour is significant through in-store manipulations. The In-Store Blueprint The top selling brands don’t leave the opportunity to catch a consumer’s attention up to chance. Instead, they meticulously plan an ideal layout for how their product will be displayed in different retail environments. These visual display blueprints are most commonly known as planograms. A Planogram is a visual merchandising tool or schematic that details how a product should be displayed in a supermarket or retail store. From our research, roughly 50% of in-store growth opportunity for CPG brands comes from availability, while 30% comes from visibility, and 15% comes from brand experience. Having effective planograms in place is the first step towards optimising each of these three key factors of in-store retail. Planning Perfect Planograms Given the importance of visual merchandising for CPG sales, combined with the fact that shelf space is such a scarce resource for retailers, taking the time to get a planogram right is well worth the investment. Brands and retailers alike know this well and so a multitude of planogram software have become readily available in the past few decades to serve their merchandising needs. Each new tool promises to help them maintain a perfect standard for how and where a Stock-Keeping Unit (SKU) should be displayed. The reality of an effective planogram, however, is a lot more nuanced and extends beyond simply ensuring that each product is adequately displayed within the available space. Far from being a static blueprint, each planogram should be easily adaptable to the realities of in-store sales data. Optimum space elasticity requires a careful balancing act between shelf space and unit sales. The inflection point, or space each SKU needs to maximise its returns, can often be elusive if the wrong assumptions are made. This can often be the case for CPG brands due to the lack of quality, up-to-date in-store shelf data. Rather than expecting to have a visual merchandising epiphany and creating the perfect planogram from the get-go, one should consider the iterative nature of optimising in-store product display. The best approach is Create → Monitor → Evaluate → Repeat. What’s Measured, Improves That which is measured improves. That which is measured and reported improves exponentially. — Karl Pearson So we know in theory that having a well thought out planogram in place for each product category is important, but how do we go about iterating on our assumptions and positively impacting in-store sales? The best way to ensure that the effort that you’ve put into your planograms is worth it is to measure and report the results, and make adjustments based on those results to assess whether different layouts result in increased sales. That sounds good in theory, but in reality, the perfectly laid out planogram that you’ve just created may not survive a real life retail environment, where products are constantly moved and replaced by customers and store staff throughout each day. What is needed is a system for ensuring the enforcement of in-store compliance with your most up-to-date set of planograms. A system that gives you real-time insights into on-shelf compliance as well as data on in-store sales. Planogram Compliance: The Bedrock of Smart Merchandising Ensuring ongoing planogram compliance means actively monitoring the shelves upon which your product is placed as often as possible. Once you’re happy that the ideal layout is being adhered to, you can then reliably assess the store sales data and make informed decisions as to the best planogram changes that can boost profitability. The most popular approaches are either: Having a dedicated in-house team that carries out these planogram compliance checks at regular intervals across all of the locations where your product is sold. While this approach can be reliable, from a process and data gathering point of view, it is unnecessarily onerous and results in very large overheads. or You could try outsourcing the work on a crowdsourcing platform. This approach is often accompanied with inconsistencies in the process as well as the resulting data. A reliable on-shelf data source is crucial for effective planogram compliance. There is, however, a third option which is proving to be the most lucrative for both CPG labels and the retailers that stock them. This third option is automation. Real-Time Shelf Monitoring Automation removes the unnecessary human cost that real-time planogram compliance demands, saving you both time and money. Nowadays, consumers spend seconds in front of any given in-store shelf display. Seeing the shelf as a customer does is critical in order for retailers and CPG brands to make meaningful merchandising decisions. While the automation of the creation of planograms has helped ease the mammoth task of in-store shelf compliance to a degree, brands are quickly realising the importance of going beyond simple planogram creation to achieve truly sustainable planogram compliance. To tackle the challenge of replacing manual visual inspection by humans, the most innovative brands are turning to Computer Vision (CV) to help automate the process. Computer Vision augments planograms with state-of-the-art image processing techniques and artificial intelligence to enable seamless automation of in-store brand compliance. This means real-time shelf monitoring that results in total planogram compliance whilst helping drive increased sales, brand optimisation, and vendor accountability. Neurolabs is taking this approach a step further by virtualising each CPG, helping them create a more efficient and effective process for automating planogram compliance by optimising the underlying data. This process is known as Synthetic Computer Vision (SCV). Getting Visual with Visual Merchandising Synthetic Computer Vision is the culmination of 60 years of advanced research into artificial intelligence and 3D geometrical mapping. The result is software that teaches computers how to interpret what they see in the real world for real-time shelf analysis. It does this by training its image detection AI algorithms using synthetic data instead of real data. In layman’s terms, it provides sight to computers and allows them to automate visual-based tasks such as in-store planogram compliance. It does so by using virtual 3D models of CPG products as the training data for its product detection software. For retailers, it automates the operational decisions and processes that are traditionally carried out manually by supermarket staff. For CPG brands, it automates in-store planogram compliance checks, provides them with real-time insights, and gives them access to a full catalog of virtual recreations of their products. Neurolabs utilises SCV in their software which automates On-Shelf Availability and Planogram Compliance, resulting in happier customers and increased revenue. The brands that have successfully used ReShelf to manage Planogram Compliance are already reaping the rewards of the future of retail technology. Virtualised Consumer Packaged Goods ReShelf uses Synthetic Computer Vision technology to carry out real-time shelf monitoring and automated planogram compliance checks on any of the Stock-Keeping Units (SKUs) that it detects. ReShelf is powered by Virtual Reality games engines that generate interactive digital 3D models of each SKU. These 3D models are used to train the product detection software, ReShelf, to identify whether a display is conforming to its associated planogram. Using these virtual 3D models of supermarket products in this way, to train AI-powered computer vision algorithms to carry out SKU-level detections, is a groundbreaking new approach to planogram compliance. Synthetic Computer Vision software like Neurolabs’ ReShelf makes the on-shelf product detection process faster, more cost-effective, and truly scalable when compared to other automation solutions. An Adaptable Solution Due to the fact that the data used to train Neurolabs’ computer vision models is synthetic, ReShelf does not require the manual effort of retraining the AI model with new images of a product every time the packaging changes. Instead of the time-consuming practice of gathering new real data, the use of synthetically generated data (in this case the easy-changeable 3D model of a CPG product) means the process is radically faster. The result is a solution that can recognise product changes before the product hits the shelves. Automated Planogram Compliance in Action At its most basic level, automated planogram compliance involves hardware, in the form of in-store cameras, that are pointed towards the supermarket shelves. These cameras collect images which act as input data for Neurolabs’ product detection algorithms. The real-time data on a shelf is fed into the Neurolabs platform and the Synthetic Computer Vision software (known as ReShelf) then runs detections on the images to determine if the product presence and placement complies with the most up-to-date planogram. This detection data can then be accessed from the Neurolabs’ platform via API in the retailer’s automation software of choice, giving you endless options as to what you can do with the analysed shelf and product data. For example, you may wish to automate alerts to in-store staff to correct a display that does not comply with its planogram. This is made seamless using the Neurolabs platform. You can check out our guide on How to Create a Planogram with Neurolabs or the video below for more detailed information on the process. A quick demo of how the Neurolabs platform helps automate planogram compliance. Automation as a Competitive Advantage Neurolabs is helping put an end to retail inefficiency and helping CPG brands thrive in an increasingly competitive landscape with the savvy use of visual-based automation technology. They are building a truly scalable Computer Vision technology for the high-speed, high-change grocery industry. With access to more than 100,000 different SKUs, Neurolabs is your ticket to seamless on-shelf insights and automation at scale. The most innovative retailers and CPG brands are taking action now by turning planogram compliance into a clear competitive advantage that pleases both customers and staff alike. Retailers and CPG brands who embrace the future of retail technology are already witnessing the brand-enhancing benefits of automated planogram compliance. The question then is not whether to implement automation technology, such as Synthetic Computer Vision, into your visual merchandising strategy but when to do it. Sources: [1] The Smart Shelf Report, Nielsen, 2020. Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. Neurolabs helps puts an end to Out-Of-Stocks and automates Planogram Compliance using a powerful combination of computer vision and synthetic data, improving customer experience, enhancing brands, and increasing revenue.

Waving goodbye to Out-of-Stocks 👋 The Modern Supermarket: Adapt to Survive “It is not the strongest of the species that survives, nor the most intelligent that survives. It is the one that is most adaptable to change.” - Charles Darwin The retail landscape is an ever-changing one. Even the biggest players in retail face a daily battle to maintain their position in the market. But, today’s largest supermarkets may not hold their position for long simply because of their gargantuan size. In fact, most of the largest retailers find it difficult to adapt quickly enough to the rapidly evolving demands of the modern retail customer, one that expects convenience and availability at all times. Take the emergence of the multitude of on-demand grocery startups and their innovative use of dark stores as a clear sign that the retail industry is rife for disruption. For the incumbents in the grocery space, adaptability and rapid innovation are simply crucial for survival. An Automated Response to Change Making the necessary operational changes required to meet ever-shifting consumer trends is a daunting task. Retail is an industry in constant flux and the pace of innovation can make it difficult for even the largest and most capable of retailers to keep up with. For successful supermarket groups, maintaining a share of the retail market means adapting and innovating in three key areas: people, process, and technology. One retailer in particular, Auchan, is leading the charge and innovating on all fronts. Despite the rapidly changing demands of the grocery sector, their savvy use of the latest and most capable automation technology allows them to continue to do what their brand is known best for, keeping their customers happy. Auchan: Leading the Way in Grocery Store Innovation In the grocery business for over 55 years, French multinational retail group, Auchan, is no newcomer when it comes to meeting constantly changing consumer expectations. Embracing the digital transition is at the heart of their strategy to succeed under increasing customer demand for reliable in-store availability and instant convenience. Empowering their people with the right processes and tools to get their job done most effectively was a priority as they set out to optimise On-Shelf Availability (OSA) in their stores. Auchan takes a very proactive approach when it comes to choosing the right system for improving in-store experience with digitisation. They are diligent and strategic when it comes to choosing a solution that will withstand the test of time and easily scale across their many locations. To maintain optimum in-store throughput and to help preserve their long-standing reputation for reliability, they have turned to the productivity-increasing promises of automation. Auchan is trialling Neurolabs’ ZIA technology to monitor its shelves in real time for On-Shelf Availability and Planogram Compliance. Enter Synthetic Computer Vision Cashierless checkouts get a ton of mainstream media attention, and for good reason. The technology radically improves throughput for retailers, removing unnecessary bottlenecks with the best that retail automation currently has to offer. It is undoubtedly worthy of the proverbial pedestal but there is another piece of retail automation technology, one that is quickly disrupting the status quo for in-store availability, that is equally worthy  -  Synthetic Computer Vision (SCV). SCV is the culmination of 60 years of advanced research into artificial intelligence and 3D geometrical mapping. The result is software that teaches computers how to interpret what they see in the real world for real-time shelf analysis. Automation in Sight In layman’s terms, it provides sight to computers and allows them to automate visual-based tasks. For retailers, it automates the operational decisions and processes that are traditionally carried out manually by supermarket staff. Neurolabs utilises SCV in their product, which automates On-Shelf Availability and Planogram Compliance, resulting in happier customers and increased revenue. Auchan has successfully trialled ZIA (Zero Image Annotations) to manage On-Shelf Availability and are already reaping the rewards of the future of retail technology. On-Shelf Innovation at Auchan Auchan is leading the charge in retail innovation by trialling Neurolabs’ Synthetic Computer Vision technology. The goal being to put an end to the Out-Of-Stock problem for good. Increased pressure on their stores to deliver outstanding customer experience meant they needed to do more than just identify gaps on shelves and fill them. To avoid simply reacting to stockouts and to ensure that a truly proactive solution was implemented, Auchan needed to address the root cause of any Out-Of-Stocks that occurred in their stores. This meant identifying and addressing fundamental process issues between their front-stores and the rest of their supply chain, requiring the integration of their stock, order, planogram, and product catalogue databases. Neurolabs’ ZIA software helped them do just that. Executing A Successful Trial As part of a trial deployment in one of Auchan’s stores in Romania, Neurolabs teamed up with, Robotic Process Automation giant, UiPath to create a solution that was tailored to the requirements of their specific supermarket environment. At its most basic level, the implemented On-Shelf Availability solution involves hardware, in the form of in-store cameras, that are pointed towards the supermarket shelves. These cameras collect images which act as input data for Neurolabs’ ZIA. Our Synthetic Computer Vision software then runs detections on these images to determine if there are any products that are low or out of stock. This detection data can then be accessed from Neurolabs’ ZIA via API in the retailer’s automation software of choice. Automation Without Limits Empowered with this real-time product detection data, the supermarket can automate processes such as instantly notifying store staff of a product that is low or out of stock so that they can replenish the shelves as soon as possible. It also provides the store with access to the most recent and useful analytics on their inventory to make the most effective decisions. This helps store managers focus on proactive decision-making versus simply reacting to in-store inventory fluctuations on the fly. This holistic approach to in-store availability and inventory management is the new necessity for supermarkets to operate at maximum efficiency. Automation-enabled smart workflows with actionable insights like this are the future for supermarkets that hope to thrive in the retail industry. Before ZIA Before the trial, Auchan had store employees manually check each aisle and record the stock availability of an SKU (Stock-Keeping Unit) at pre-agreed intervals. Besides the fact that it is such an onerous process, Auchan had little to none shelf visibility in between these inventory checking sessions. These stock level records were then used by the Auchan team to manually compare across multiple different internal systems with the goal of understanding why there is a gap on a shelf to begin with. This is workflow standard practice for the majority of supermarkets. After ZIA The first change that Neurolabs helped introduce for Auchan was a way to have full visibility across each shelf at any time. Secondly we created an automated workflow that identified the root cause of each Out-Of-Stock. Based on the gathered insights, certain actions are now automated and the right information is automatically shared with the right people at the right time, empowering Auchan’s in-store staff to address the issues the moment they occur. The result for Auchan is real-time visibility of their shelves and an end to Out-Of-Stocks. More importantly this means a more efficient workforce, increased customer satisfaction, and a significant boost in sales. Digitised Consumer Packaged Goods ZIA uses SCV technology to carry out real-time shelf monitoring and automated root cause analysis on any of the missing Stock-Keeping Units (SKUs) that it detects. ZIA is powered by Virtual Reality games engines that generate interactive digital 3D models of each SKU which are then used as the data to identify when a product is Out-Of-Stock. Using these virtual 3D models of supermarket products in this way, to train AI-powered computer vision algorithms to carry out SKU-level detections, is a groundbreaking new approach to On-Shelf Availability. Synthetic Computer Vision software like Neurolabs’ ZIA makes the on-shelf product detection process faster, more cost-effective, and truly scalable when compared to other automation solutions. A Flexible Solution Due to the fact that the data used to train Neurolabs’ computer vision models is synthetic, ZIA does not require the manual effort of retraining the AI model with new images of a product every time the packaging changes. Instead of the time-consuming practice of gathering new real data, the use of synthetically generated data (in this case the easy-changeable 3D model of a supermarket product) means the process is radically faster. The result is a solution that can recognise product changes before they even hit the shelves. Beyond Inventory Visibility Neurolabs isn’t stopping at On-Shelf Availability and Planogram Compliance. Their collaboration with UiPath unleashes the best of Synthetic Computer Vision and Robotic Process Automation that enables a holistic approach to inventory automation for retailers. This helps them get to the root of the inventory problem in a retailer’s supply chain. It also provides them with true flexibility in terms of transforming the shelf insights they collect into a wide array of rapid and impactful actions for the retailer. This is due to the ease of implementation with the majority of retail IT systems that UiPath’s automation software provides. The ability to simply automate visual-based tasks by combining Neurolabs’ Synthetic Computer Vision software with UiPath’s automation technology means that you don’t have to stop at in-store optimisation. In fact, this approach can easily be applied to the automation of each stage of a consumer packaged good’s journey, from manufacturing and distribution, to checkout, recycling, and much more. The Necessity for Visual-Based Automation With the rising costs of labour combined with the increasing demands of consumers, automation is now becoming a necessity for the top supermarkets to stay competitive. The good thing is that the technology has reached a tipping point and today you can easily access world class automation with truly compelling economies of scale. The traditional approach to On-Shelf Availability has resulted in an average Out-of-Stock rate of 8%, meaning one out of every 13 products is not available for sale when a consumer wants it. This rate rises further to 10%+ for discounted products. With this reality in mind, it’s clear that a large opportunity exists for those who are willing to innovate with a more sophisticated and capable solution to staff-intensive visual-based work. The question then is not whether to implement automation technology, such as SCV, into your in-store operations but when to do it. The Time for Retail Automation is Now Today, 5% of all sales are lost due to Out-Of-Stocks, with, on average, 8% of SKUs remaining Out-Of-Stock. The biggest headache here is that the issue simply does not have to exist with the right use of technology. Neurolabs’ is helping put an end to retail inefficiency and helping supermarkets thrive in an increasingly competitive landscape with the savvy use of visual-based automation technology. The most innovative retailers like Auchan are taking action now by turning their in-store inventory problem into a clear competitive advantage that pleases both customers and staff alike. Retailers who embrace the future of retail technology in this way aren’t just adapting to survive, they are ensuring a future in which their retail business thrives. At Neurolabs, we are revolutionising in-store retail performance with our advanced image recognition technology, ZIA. Our cutting-edge technology enables retailers, field marketing agencies and CPG brands to optimise store execution, enhance the customer experience, and boost revenue as we build the most comprehensive 3D asset library for product recognition in the CPG industry.

The Best Way to Prevent Stockouts in 2022 Out-Of-Stock, Out-Of-Mind, Out-Of-Business The definition of a “supermarket”, according to the Oxford dictionary, is a “large shop that sells food, drinks and goods used in the home. People choose what they want from the shelves and pay for it as they leave.” This basic description details the simplest function of the grocery business as far as the consumer is concerned. This is a supermarket’s fundamental reason for existence and it has been since the very first supermarket, the Piggly Wiggly store, opened its doors on the 6th of September 1916 in Memphis, Tennessee. The average customer simply wishes to be able to obtain the common goods that they want from their store of choice’s shelves. A very low expectation as we approach the year 2022 or, at least, one would think. Today, over one hundred years after the first supermarket opened its doors, the average Out-Of-Stock rate is 8%. This is an unnecessarily high loss of sales for retailers given the sophisticated retail technology that currently exists. It means that one out of every thirteen products is not purchasable at the time when a customer wishes to purchase it in the average supermarket. This rate increases to 10%+ when it comes to discounted products or products that are part of a promotional activity. The Real Cost of Empty Shelves Needless to say, retailers and their suppliers lose out big time from a revenue perspective. The current cost of Out-Of-Stock products is $634 billion per year for the global retail sector. That’s more than the entire GDP of the majority of countries in the world. For the average retailer, that’s a loss of 5% of in-store sales due to stockouts alone. Loss of sales for retailers aside, consider the impact of Out-Of-Stock products on the customer experience and a customer’s relationship with your brand. 31% of consumers go on to buy from another store when they experience a stockout, which means they become a potential churn risk as they take their business to another retailer. The same goes for the suppliers of Out-Of-Stock products and their associated brands with 26% of consumers likely to switch to another brand and potentially never switch back. Over one hundred years have passed since the opening of the first supermarket and despite so much time for advancement, it’s easy to see that the majority of retailers still fail to offer the most basic service to their customers. Most supermarkets and retail stores still fail to maintain optimum stock levels and prevent Out-Of-Stocks. The modern supermarket is broken. To fix it, retailers need to implement the best on-shelf availability technology in retail. Let’s take a look at how. Starting With What You Know In order to diagnose on-shelf availability issues effectively, retailers should start by collecting the appropriate data by looking at their current operating model. This means understanding the real-time situation of on-shelf product availability in your stores and identifying where the gaps exist. This doesn’t have to be complicated. We recommend starting manually before you move on to more sophisticated, automated retail solutions. By doing so, you can assess the real impact of Out-Of-Stock products for your specific retail business. By carrying out a dedicated, manual audit of shelf availability over a determined period of time, you can sample the problem and get a real feel for the extent of sales your business is losing as a result of stockouts. In practice this means deploying a dedicated team to monitor stock levels for a specific store at all times during a sampling period. The team should restock product as soon as a gap occurs on a shelf. Take the increased sales results from this experiment and compare them to the same time period in previous months and you’ll quickly see the benefits of tackling the problem with a more robust, long-term solution that prevents unnecessary losses. This exercise will help identify potential problem areas in store as some product lines are likely to be causing more of an issue than others. This also has the additional benefit of helping you improve any supplier issues that may exist in your stores. Analysing the Gaps Once you’ve identified that gaps exist and where they exist, you can then begin to consider why they exist. Are there patterns for a specific line of products being Out-Of-Stock? Do you notice trends when stockouts have typically occurred in the past? Is adequate demand forecasting being carried out by your team to plan effectively and avoid Out-Of-Stock situations? Have you considered the lead times for each SKU (stock-keeping unit) and ensured that you have established them sufficiently with your suppliers? Is the product missing from the shelf because a store employee didn’t bring it from the back store? Is the product Out-Of-Stock because the SKU is not active anymore? Is there an issue with the supplier which has resulted in a late delivery? Was the correct amount of product ordered to begin with? These are just some of the many questions one should consider when effectively addressing product availability. As you seek answers to these questions and continue to collect more data on the stockout problem, you will also begin to see how unnecessarily difficult this information is to obtain when you need it. This is due to the many different systems and stakeholders involved in getting each product to shelf, often hindered further by legacy issues that are inevitable for mature retail chains. With this in mind, it’s time to consider what the best on-shelf availability solution looks like for your retail business in 2022. Building an Optimum On-Shelf Availability System Take a look at how you are currently managing Out-Of-Stocks in each of your stores. Consider what can be automated. Repetitive, manual tasks are the perfect candidate for automation. Having someone walk down each aisle and visually, or even with the use of a barcode scanner, identify gaps on shelves so that they can be filled is an unnecessarily onerous task for something that can be easily automated. Processes like this are also particularly prone to human error which the use of the right technology removes entirely. At any time, you should be able to easily access a real-time view of each shelf and product in any your retail stores. It should provide you with current shelf stock levels per SKU, the amount of backup stock in storage, expected throughput for a given period, and the option to visually inspect any shelf remotely if you desire. This is true, real-time shelf monitoring that any modern on-shelf availability solution should provide. Human + Machine = The Perfect Team The best on-shelf availability system is also the one that you don’t even notice exists, one whose infrastructure is unnoticeable to the average customer. It is a perfect blend of people, process and technology working seamlessly together to achieve a common goal. It isn’t about automating people out of a job, it’s about enabling your workforce to perform at their best. It also shifts staff focus from menial tasks to more complex, engaging work that humans are best at. You should use technology to do what it does best, empower your staff. An effective solution should be able to send automated notifications to store staff, informing them of a stockout as it occurs. From Reactive to Proactive Stock Management The final consideration is whether your on-shelf availability solution allows you to simply react to a stockout or get proactive with a deep root cause analysis. This goes beyond preventing Out-Of-Stock products to having the right stock available in-store according to ever changing demand. Instead of reacting to issues in your supply chain you should seek to understand the underlying problem and address the root cause so that the stockout never happens again. For retailers, real-time shelf monitoring is really just the beginning. A solution that connects with the different components of your supply chain is one that is truly powerful and effective. It should be able to complete Out-Of-Stock root cause analysis to determine the reason for specific stockouts so that your staff can take action to prevent them from happening again. Insights In Sight This level of insight helps improve supplier relationships and gives you a lot more control over the performance of each store at the SKU level. By having a detailed, real-time view of your on-shelf inventory as well as expected sales data you can then decide what the most effective form of inventory storage is for each of your locations whether it’s consignment inventory, vendor managed inventory, safety stock etc. The retail solution described above can be achieved using your existing systems and full-time dedicated staff to ensure that no Out-Of-Stock issues occur during daily operations (human error aside) but the human cost of such an endeavour inevitably reaches diminishing returns pretty quickly. Fit for purpose, automated on-shelf availability technology, on the other hand, allows you to tackle the problem effectively and achieve economies of scale. This is all made possible by the power of artificial intelligence and a powerful new technology called Synthetic Computer Vision. An AI-Powered Solution Neurolabs is automating on-shelf availability at scale using the approach described above. We deploy a powerful combination of Artificial Intelligence and Computer Vision to create real-time shelf monitoring and Out-Of-Stock root cause analysis for supermarkets and retail stores. We completely digitise each of your SKUs by creating a virtual 3D model of each of them. We then use these 3D models as the synthetic data to train our AI software to detect the real versions on your supermarket’s shelves via in-store cameras. This is the first step towards truly automated, real-time shelf monitoring that puts an end to Out-Of-Stocks, using Synthetic Computer Vision. Automating Real World Retail With Virtualisation We specialise in the use of synthetic data as it allows us to rapidly scale our solution across thousands of SKUs with ease. This is radically faster than the traditional computer vision approach. It also means that our software can adapt to product changes before a product hits the shelves, meaning no interruption to service if a product’s packaging is updated. We use cameras to carry out the detections. Depending on existing infrastructure, existing hardware can be used, otherwise new cameras are installed to monitor shelves in real-time. We have found that fixed cameras result in higher performance than a mobile solution. Empowering The Retail Workforce When an on-shelf stockout is detected, an automated alert is sent to store staff to inform them of the issue so it can be resolved ASAP. A number of automated checks are then carried out with each element of your supply chain system to determine the root cause. The results of this are then sent to the store manager for resolution. This gives each store real-time visibility of on-shelf availability, allows them to respond to Out-Of-Stock products instantaneously, and most importantly, helps prevent future stockouts from occurring by tackling the individual underlying issue. Neurolabs’ On-Shelf Availability solution does more than just check stock on shelves: It automates the manual process of on-shelf stock checking It helps get to the root cause of an Out-Of-Stock It increases revenue per store It creates happier customers It is easily scalable per store and across retail locations It is a no code technology with option to take a peak behind the scenes It avoids data privacy issues by using synthetic data We integrate with any other retail system seamlessly (We work seamlessly with RPA technology such as UiPath to create bespoke automations) It is rapidly adaptable to product changes (Detects new products and packaging before they hit the shelves) It performs effectively in challenging retail production environments (In places where traditional computer vision (CV) solutions struggle) It is extremely precise vs conventional CV methods It is cost-effective The Future of Retail Technology As we enter 2022, Out-Of-Stock products in supermarkets need to become a thing of the past. The use of AI technology is proven to resolve the issue. Effective implementation presents a very big opportunity for successful retailers who are willing to innovate with a sophisticated and capable solution in the retail space. Using the Synthetic Computer Vision approach described above, the technology can be used for more than just monitoring stock levels on store shelves. It is set to become an important retail trend in the years to come. With this unique approach to product detection, you can automate each stage of an SKUs journey, from manufacturing and distribution, to in-store inventory and checkout. The real question then is not whether or not you should automate your on-shelf availability, but when? Time For A Check Up? How are you currently managing on-shelf availability for your retail business? Our team of experts is laser focused on solving complex retail challenges like on-shelf availability so we’d love to hear from you. We work with the fastest growing supermarkets and retail technology partners in the industry to implement state-of-the-art retail automation solutions. Any processes in your supermarket that involve the manual handling of an SKU could be the perfect candidate for applying Synthetic Computer Vision and unlocking the benefits of automated workflows for your retail business. The use of Synthetic Data drastically shortens the implementation time of our on-shelf availability solution when compared with the main alternatives on the market today. Even if you’re not ready to make the jump to implementing an automated system to handle your out-of-stocks just yet, we’re always interested in discussing the best practices for improving retail processes at scale. For tips and advice on the best ways to avoid stockouts, reach out to the Neurolabs team and we’ll be happy to help! Retailers worldwide lose a mind-blowing $634 Billion annually due to the cost of poor inventory management with 5% of all sales lost due to Out-Of-Stocks alone. Neurolabs helps puts an end to Out-Of-Stocks using a powerful combination of computer vision and synthetic data, improving customer experience and increasing revenue.