Gain Actionable Sell-Out Insights with the Power of AI and Edge Computing

Watch the video

From Shelf to Data Analysis: A New Frontier in Retail

Eye-Shelf is a solution that provides valuable sell-out information by leveraging the power of AI and edge computing.

Equipped with high-performance cameras and computational boards, it can recognize products picked up from shelves or refrigerated displays and associate them with the shopper’s general characteristics.

Its advanced Deep Learning (AI) models are carefully trained to recognize specific products and classify the gender and age range of shoppers.

The extracted information is then used for the following tasks:

  1. Automating restocking prompted by a "stock-out"

  2. Collecting sell-out data by cross-referencing purchases with shopper gender

  3. Determining the age of the person taking the item

Innovation at Every Level

Eye-Shelf incorporates computer vision techniques that leverage the power of neural networks to recognize all objects and faces captured by the cameras. Since deep learning models require significant resources, the hardware was selected accordingly.

This means that we selected highly advanced components specifically designed for optimum support of neural networks. Our goal was to develop a solution based on edge computing—the ability of a system to perform analysis directly on the display – resulting in a decentralized and highly flexible solution.

Benefits

The Benefits of the Eye-Shelf Solution

Eye-Shelf can be integrated into existing structures using dedicated kits, and the high speed of the product recognition models enables real-time analysis with 90% accuracy. Furthermore, all generated reports are easily accessible via a web interface – at any time and from any location.

Our primary target includes goods manufacturers aiming to drive adoption through their distribution networks, manufacturers of display stands or shelves, and supermarkets where Eye-Shelf can be effortlessly integrated into pre-existing setups.

The development of the solution required the contribution of various specialists: Data Engineers handled data cleaning, Data Scientists worked on data augmentation and training deep learning models, while AI Engineers focused on developing the software and integrating it with the AI models and highly specialized hardware.