Object Dimensioning via User-Confirmed Corner Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing imaging systems for dimensioning box objects in inventory environments are inefficient due to the time-consuming process of identifying actual corners among potential corners, leading to potential errors in dimensioning.
Innovation Solution
A system comprising multiple cameras and a processor that captures image data, analyzes it to identify candidate corners, and uses user input to confirm actual corners, thereby reducing processing time and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing imaging systems identify corners by analyzing all potential corners, then corner identification is performed, but the process takes a very long time
Solution Approach 1:
The system performs preliminary actions by having the user manually indicate corner locations before full dimensioning processing begins. This preliminary user input narrows down the search space from all potential corners to only the actual corners of interest, eliminating the time-consuming exhaustive search while maintaining accurate corner identification.
2Productivity
If existing imaging systems automatically identify corners from image data, then corner detection is performed, but errors occur when actual corners are incorrectly identified
Solution Approach 1:
The system incorporates feedback by requiring user confirmation of corner locations. The user reviews the system's preliminary corner detection results and provides corrective input by indicating the actual corner positions. This feedback loop ensures high reliability in corner identification while maintaining improved productivity compared to purely manual methods.
Solution Approach 2:
The system performs preliminary automatic corner detection to generate candidate corner positions, then uses user input to confirm or correct these positions. This two-stage approach combines the speed of automatic detection with the accuracy of human verification, resolving the contradiction between productivity and reliability.
3Measurement precision
If manual corner identification is used, then accurate corner locations are obtained, but the dimensioning process becomes very time-consuming
Solution Approach 1:
The system performs preliminary automatic corner detection to generate candidate corner positions before requiring user input. This preliminary action filters out most incorrect candidates, so the user only needs to confirm or make minor adjustments to a shortlist of potential corners. This dramatically reduces the time required compared to purely manual identification while maintaining high accuracy.
Data Source
AI summary
Methods and apparatus for rapidly dimensioning an object are provided. An example method includes capturing, by a plurality of cameras, image data representative of an object; analyzing, by a processor, the image data to identify a plurality of candidate corners of the object; detecting, by the processor, a proximity of an appendage to each of the candidate corners; confirming, by the processor, based on respective proximities of the appendage to the candidate corners of the object, that a first one of the candidate corners is a corner of the object; and calculating, by the processor, based on the confirmed corner of the object, a dimension of the object.