Planogram-Based Shelf Stock Tracking With Fixed Cameras
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current stock keeping methods in retail stores lack efficiency in tracking inventory with low-resolution images from a small population of fixed cameras, requiring significant network bandwidth and infrastructure changes, and struggle to accurately identify product types and quantities in images with low object-level resolution.
Innovation Solution
A method that uses a computer system to access and process images from fixed cameras and mobile robotic systems, leveraging a planogram to identify product types and quantities by comparing extracted features with product models, even in low-resolution images, and updates stock conditions in real-time, allowing for efficient restocking prompts and minimal infrastructure changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If fixed cameras with low-resolution images are used for stock tracking, then infrastructure changes are minimized, but measurement precision deteriorates
Solution Approach 1:
The system performs preliminary actions by capturing images at multiple time points (first time and second time) and using planogram data to pre-establish expected product configurations. This allows the system to anticipate and prepare for inventory changes before they occur, enabling accurate tracking even with low-resolution imagery from fixed cameras.
Solution Approach 2:
The system implements feedback mechanisms by comparing images captured at different time points and using detection results to update inventory records. The computer system continuously monitors changes in product presence, orientation, and quantity, and uses this feedback to maintain accurate real-time inventory tracking despite the limitations of fixed camera resolution.
2Measurement precision
If more cameras are deployed to improve coverage, then measurement precision improves, but network bandwidth requirements increase
Solution Approach 1:
The system extracts only the essential information needed for inventory tracking by comparing images captured at different time points and focusing on detecting changes in product presence and orientation. This selective extraction approach allows accurate inventory monitoring using data from fixed cameras without requiring high-bandwidth continuous streaming of all image data.
Solution Approach 2:
The system uses periodic action by capturing images at specific time intervals (first time and second time) rather than continuously streaming video. This periodic sampling approach reduces network bandwidth requirements while still enabling accurate detection of inventory changes that occur between sampling points.
3Measurement precision
If mobile robotic systems are used instead of fixed cameras, then measurement precision improves, but device complexity increases
Solution Approach 1:
The system achieves universality by making the mobile robotic system capable of performing multiple functions: capturing high-resolution images for detailed product identification, navigating to different locations autonomously, and integrating with the existing fixed camera network. This multi-functional design allows a single system to replace or supplement multiple fixed cameras while providing superior measurement precision.
Solution Approach 2:
The system applies dynamics by enabling the robotic platform to move and reposition itself autonomously within the store environment. This dynamic capability allows the system to adapt to changing inventory locations and capture images from optimal angles, improving measurement precision while maintaining manageable device complexity through automated navigation.
Data Source
AI summary
One variation of a method for stock keeping in a store includes: accessing an image captured by a fixed camera within the store; retrieving a field of view of the fixed camera; estimating a segment of an inventory structure in the store depicted in the image based on a projection of the field of view onto a planogram of the store; identifying a set of slots within the inventory structure segment; retrieving a product model representing a set of visual characteristics of a product type assigned to a slot, in the set of slots, by the planogram; extracting a constellation of features from the image; if the constellation of features approximates the set of visual characteristics in the product model, detecting presence of a product unit of the product type occupying the inventory structure segment; and representing presence of the product unit, occupying the inventory structure segment, in a realogram.