Shelf Scene Segmentation Using Segment Tags and Product Templates
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 preexisting maps or plans, leading to inefficiencies in tracking and identifying products.
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 images based on product characteristics, enabling accurate product identification and tracking even without preexisting maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a mobile robotic system autonomously captures images of inventory structures without preexisting maps, then adaptability and versatility are improved, but device complexity and computational load increase
Solution Approach 1:
The patent divides the inventory structure image into multiple scenes based on detected segment tags and product characteristics. Each scene represents a distinct portion of the inventory structure, allowing independent processing and analysis. This segmentation reduces the overall computational complexity by breaking down the large-scale image analysis into smaller, manageable scene-level tasks.
Solution Approach 2:
The system performs preliminary detection of segment tags and slot tags before conducting detailed product identification. By pre-segmenting the inventory structure and identifying structural features first, the system prepares the data in advance, reducing the computational burden during the actual product tracking and analysis phases.
2Measurement precision
If scene segmentation is applied to segment product units based on characteristics, then measurement precision and reliability are improved, but device complexity increases
Solution Approach 1:
The patent applies different processing methods and criteria to different scenes based on their specific characteristics. Each scene is analyzed with localized parameters and product templates appropriate to that specific inventory portion, improving measurement precision for product identification while managing complexity through targeted rather than universal processing.
Solution Approach 2:
The system adjusts processing parameters dynamically based on scene characteristics and detected product features. By changing parameters such as template matching thresholds, segmentation criteria, and detection sensitivity according to the specific scene context, the system achieves high precision without requiring uniformly complex processing across all scenes.
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.