Shelf Edge Detection Using Depth Sensor Guide Element Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In retail environments, detecting the edges of support surfaces, such as shelves, is complicated by factors like varying product shapes and orientations, lighting variations, and obstructions, making it difficult to accurately identify shelf edges for inventory management and stock replenishment.
Innovation Solution
A method and system using a mobile automation apparatus equipped with depth sensors and an imaging controller to obtain and process depth measurements, selecting candidate measurements based on expected proximity and orientation, fitting a guide element, and detecting shelf edges by evaluating the proximity between candidate measurements and the guide element.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image processing methods are used to detect shelf edges, then the system is simple to implement, but the detection accuracy deteriorates due to lighting variations, product obstructions, and variable shelf orientations
Solution Approach 1:
The patent transitions from 2D image processing to 3D depth measurement by incorporating depth sensors (time-of-flight cameras, structured light sensors, or stereo vision systems). This dimensional change allows the system to detect shelf edges based on depth discontinuities rather than relying on 2D image intensity variations, thereby overcoming lighting variations and product obstructions that plague traditional methods.
Solution Approach 2:
The patent replaces traditional mechanical/optical image processing methods with active sensing technologies that emit and measure light time-of-flight or phase shifts. This substitution enables direct depth measurement, providing robust edge detection that is insensitive to ambient lighting conditions and occlusions by products on the shelf.
2Measurement precision
If multiple depth measurements and guide elements are used to improve detection accuracy, then the measurement precision improves, but the processing time and computational complexity increase
Solution Approach 1:
The patent performs preliminary filtering of depth measurements by selecting only those points that lie within expected geometric constraints (e.g., within a certain depth range from the sensor, or within expected angular ranges). This preliminary action reduces the number of candidate points that require further processing, thereby maintaining detection precision while reducing overall processing time.
Solution Approach 2:
The patent segments the depth measurement data by dividing the field of view into multiple regions or by processing depth points in groups based on their spatial distribution. This segmentation allows the system to apply guide element fitting locally to subsets of data rather than processing all depth measurements globally, reducing computational complexity while maintaining overall detection accuracy.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Accurately identifies shelf edges despite complex environments, enabling effective inventory management and stock status notifications, improving the efficiency of product labeling and stock replenishment processes.
Implementation Method 1
a depth sensor to obtain a set of depth measurements
Data Source
AI summary
A method of detecting an edge of a support surface by an imaging controller includes: obtaining a plurality of depth measurements captured by a depth sensor and corresponding to an area containing the support surface; selecting, by the imaging controller, a candidate set of the depth measurements; fitting, by the imaging controller, a guide element to the candidate set of depth measurements; and detecting, by the imaging controller, an output set of the depth measurements corresponding to the edge from the candidate set of depth measurements according to a proximity between each candidate depth measurement and the guide element.