Shelf Product Matching for Automated Plug And Spread Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing inventory tracking systems in retail stores require substantial human intervention for creating and updating planograms, are inefficient in detecting misplaced or out-of-stock products, and fail to automate the process of identifying product positions and reordering needs.
Innovation Solution
A mobile, autonomous robot equipped with multiple cameras and sensors navigates store aisles to collect images, analyze panoramic views, and identify product positions, misplacements, and out-of-stock items using deep learning detectors and classifiers, enabling automated inventory tracking and dynamic enrollment of new products.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If machine vision technology with fixed cameras is used to monitor aisles, then product inventory tracking is enabled, but substantial human intervention is still required to create and update planograms manually
Solution Approach 1:
The system enables self-service by automatically extracting product information, positions, and relationships from images using deep learning detectors and classifiers. The robotic system autonomously navigates aisles, captures images, and processes them to generate and update planograms without requiring manual human intervention for planogram creation or updates
Solution Approach 2:
The patent replaces manual mechanical processes of planogram creation and updates with automated computer vision and machine learning systems. Deep learning detectors and classifiers automatically analyze images to identify products, their positions, and spatial relationships, substituting the manual task of creating and updating planograms with an automated digital system
2Reliability
If manual monitoring of product inventory is performed, then product tracking is possible, but it is expensive and time consuming
Solution Approach 1:
The robotic system enables continuous inventory monitoring by autonomously navigating store aisles and capturing images at regular intervals. The system operates continuously without interruption, providing ongoing tracking of product positions and stock levels without the time losses associated with manual periodic checks
Solution Approach 2:
The patent replaces manual inventory monitoring with an automated robotic system equipped with cameras and deep learning detection algorithms. The system automatically identifies products, their positions, and stock status, eliminating the time-consuming and costly manual monitoring process while maintaining or improving tracking accuracy
3Loss of information
If planograms are manually created and updated, then product layout information is captured, but the process is labor intensive and does not scale efficiently
Solution Approach 1:
The system creates digital copies of physical shelf layouts by capturing images with cameras and automatically extracting product information, positions, and spatial relationships through deep learning. These digital representations (planograms) are generated automatically from image data, eliminating the need for manual creation while maintaining accurate product layout information
Solution Approach 2:
The patent substitutes manual planogram creation and updates with an automated image-based system. Deep learning detectors and classifiers process captured images to automatically extract all necessary planogram information including product identification, positions, and layout relationships, dramatically improving efficiency and scalability while preserving information accuracy
Data Source
AI summary
Disclosed herein is a system and method for matching products detected in an image of a shelf. The match or non-match of the products is then used to make a determination that the products are correctly positioned on the shelf of if the positioning of the products represents a plug or spread situation.