Retail Shelf Product Identification with Image Features and Labels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing inventory tracking systems in retail stores require manual planogram creation and updates, are labor-intensive, and fail to accurately detect misplaced, stolen, or damaged products, leading to out-of-stock issues and reduced sales.
Innovation Solution
A mobile, autonomous robot equipped with multiple cameras navigates store aisles, collects images, and analyzes them to identify products, determine their status, and match them with expected positions using a feature extractor and shelf labels, automatically flagging misplacements and out-of-stock items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual planogram creation and updates are used, then system setup is straightforward, but labor intensity increases and accuracy decreases
Solution Approach 1:
The system performs self-service by automatically extracting features from product images and matching them against a database without requiring manual planogram creation or updates. The machine learning model autonomously identifies products, their positions, and statuses, eliminating the need for human intervention in routine monitoring tasks.
Solution Approach 2:
The patent replaces manual mechanical processes (creating and updating planograms by hand) with an automated electronic system using machine learning algorithms. The feature extractor and product database substitution eliminates manual labor while improving accuracy and reducing errors.
2Productivity
If manual inventory monitoring is performed, then system simplicity is maintained, but time consumption increases and productivity decreases
Solution Approach 1:
The system enables continuous automated monitoring of inventory status, product positions, and shelf conditions. The robot can operate repeatedly without interruption, providing ongoing updates on stock levels and product placement without the time losses associated with manual periodic checks.
Solution Approach 2:
Manual inventory monitoring is replaced with an automated robotic system equipped with cameras and machine learning processing. This substitution dramatically reduces the time required for inventory tracking while maintaining continuous surveillance of store conditions.
3Measurement precision
If fixed position cameras are used, then system complexity is reduced, but adaptability decreases and measurement precision worsens
Solution Approach 1:
The system transitions from static fixed cameras to a dynamic mobile robot platform that can navigate through store aisles and adjust its position. This dynamic capability allows the system to adapt to different store layouts, product placements, and lighting conditions, improving measurement precision without requiring an overly complex fixed camera network.
Solution Approach 2:
The mobile robot serves multiple functions: navigation through aisles, capturing product images, detecting shelf labels, identifying products, and monitoring inventory status. This multi-functionality consolidates what would otherwise require multiple specialized systems into a single adaptable platform.
Data Source
AI summary
Disclosed herein is a system and method of identifying products on a retail shelf using a feature extractor trained to extract features from images of products on the shelf and output identifying information regarding the product in the product image. The extracted features are compared to extracted features in a feature gallery library and a best fit match is obtained. A product ID is then assigned to the image of the product and the assigned product ID is validated by matching the product ID with product identifying information extracted from a shelf label associated with the image of the product.