Image Evaluation for Accurate Dimension Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dimensioners used in logistics for measuring cargo and inventory dimensions often capture inaccurate image data, leading to faulty apportioning and measurements, particularly due to insufficient structured light information and orientation issues, necessitating a method to evaluate and correct image data for accurate dimension computations.
Innovation Solution
The method involves capturing multiple images of an item from different perspectives, comparing measurements, and using wireframe models and surface features to recognize and correct false values, ensuring accurate dimension measurements by rejecting inaccurate data and computing mean values for correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If dimensioners capture image data from items on high speed conveyors, then productivity increases, but measurement precision deteriorates due to insufficient structured light information and orientation issues
Solution Approach 1:
The system performs preliminary evaluation of image data quality before final dimension computation. It assesses whether captured images contain sufficient structured light information and proper orientation, and only proceeds with measurements from images that meet quality criteria, thereby maintaining precision while processing high-speed conveyor items
Solution Approach 2:
The system implements feedback mechanisms by comparing multiple captured images and evaluating their quality metrics. It uses feedback from image quality assessment to determine whether to accept or reject measurements, and can trigger re-capturing when quality is insufficient, thus resolving the contradiction between speed and precision
2Measurement precision
If dimensioners rely on consistently reliable measurement accuracy, then measurement precision is improved, but device complexity increases to evaluate and correct false image values
Solution Approach 1:
The system performs self-evaluation of its own image data quality using automated algorithms to detect false values, assess structured light information sufficiency, and determine orientation adequacy. This self-service approach maintains measurement precision without requiring external complex verification systems
Solution Approach 2:
The system creates wireframe models as simplified copies of the actual items from captured images. These wireframe representations enable easier evaluation of dimension accuracy and facilitate detection of false measurements without requiring complex analysis of the original complex images
Data Source
AI summary
Images of items are evaluated. A first image of the item, having a view of two or more of its surfaces, is captured at a first time. A measurement of at least one dimension of one or more of the surfaces is computed and stored. A second image of the item, having a view of at least one of the two or more surfaces, is captured at a second time, subsequent to the first time. A measurement of the dimension is then computed and compared to the stored first measurement. The computed measurement is evaluated based on the comparison.