Shelf Scene Segmentation for Map-Free Robotic Inventory Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing inventory management systems struggle to accurately and efficiently segment product units on inventory structures within stores without relying on pre-existing maps or planograms, leading to inefficiencies in inventory tracking and product identification.
Innovation Solution
A method utilizing a mobile robotic system to autonomously capture images of inventory structures, detect segment and slot tags, and apply scene filters to segment and label product units based on image analysis, enabling accurate inventory tracking and product identification even without pre-existing maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a mobile robotic system autonomously captures images and performs scene segmentation without pre-existing maps, then inventory tracking accuracy is improved, but computational load and processing time increase
Solution Approach 1:
The image processing system divides the inventory scene into multiple segments or regions of interest, processing each segment separately rather than analyzing the entire image at once. This reduces computational complexity and processing time while maintaining accurate inventory tracking through systematic analysis of divided portions of the scene
Solution Approach 2:
The system performs preliminary actions by capturing images with properly positioned cameras before actual inventory analysis occurs. Pre-processing steps including image stabilization, normalization, and feature detection are executed beforehand to reduce the computational burden during the main inventory segmentation and identification phase
2Adaptability or versatility
If scene segmentation is performed without pre-existing maps or planograms, then system adaptability is improved, but measurement precision and product identification accuracy may deteriorate
Solution Approach 1:
The system performs self-service by automatically generating its own scene segmentation and product identification framework without relying on pre-existing maps or planograms. The robotic system captures images, detects product features, and autonomously identifies and segments inventory items through machine learning algorithms, making the system adaptable to any store layout while maintaining identification accuracy
Solution Approach 2:
The patent replaces traditional mechanical or manual inventory tracking methods with optical and computational systems. Camera-based image capture and computer vision algorithms substitute for physical inventory checks and manual record-keeping, enabling the system to adapt to any store configuration while maintaining high measurement precision through automated optical detection and analysis
Data Source
AI summary
One variation of a method for segmenting scenes of product units arranged in inventory structures within a store includes: accessing an image based on data captured by a mobile robotic system; detecting a shelving segment in the image; reading a segment identifier from a segment tag, detected in the image, arranged on the shelving segment; accessing a product template representing a product type in the set of product types assigned to the shelving segment based on the segment identifier; detecting a set of product features, in the first region of the image. In response to detecting the set of product features analogous to features of the product template: confirming presence of the unit of the first product type on the shelf in the shelving segment and appending the first product type to a list of product types presently stocked in the shelving segment.