Ranked Adaptive ROI for Machine Vision Feature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current machine vision systems are inefficient in locating visual features like barcodes due to the need to search the entire field of view, which is time-consuming and wasteful of processing power.
Innovation Solution
The system uses ranking-based adaptive region of interest (ROI) techniques to efficiently locate visual features by ranking potential ROIs based on recurrence frequency and searching within the highest ranked ROIs first, gradually expanding to the entire field of view if necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the entire field of view is searched for visual features, then the detection reliability is improved, but the processing time and computational power increase significantly
Solution Approach 1:
The field of view is segmented into multiple regions of interest (ROIs) based on historical data and recurrence patterns. Instead of searching the entire FOV uniformly, the system divides it into high-probability ROIs that are searched first, maintaining detection reliability while reducing overall processing time.
Solution Approach 2:
The system performs preliminary actions by pre-identifying and ranking ROIs based on historical recurrence data before actual visual feature detection. This preliminary ranking allows the system to prioritize search areas, ensuring that high-probability regions are examined first, thus reducing processing time without compromising reliability.
2Reliability
If the entire field of view is searched for visual features, then the detection completeness is improved, but the computational power consumption increases
Solution Approach 1:
The computational workload is segmented by dividing the FOV into ranked ROIs. The system processes only the most relevant ROIs first based on historical data, significantly reducing computational power consumption while maintaining detection completeness through iterative expansion to lower-ranked ROIs if needed.
Solution Approach 2:
The system applies partial action by processing only the necessary portion of the FOV (top-ranked ROIs) rather than the entire area. This reduces computational power consumption while maintaining detection completeness, as the system can iteratively expand to include more ROIs only if visual features are not found in higher-priority regions.
3Productivity
If multiple regions of interest are ranked and searched iteratively, then the processing efficiency is improved, but the device complexity increases
Solution Approach 1:
The system performs preliminary ranking of ROIs based on historical recurrence data before actual detection. This preliminary organization simplifies the iterative search process by pre-establishing a priority order, improving processing efficiency without significantly increasing system complexity.
Solution Approach 2:
The system uses feedback from historical detection data to continuously refine and update ROI rankings. This feedback mechanism improves processing efficiency by learning from past patterns, while the complexity increase is managed through automated algorithms that adapt rankings based on recurrence frequencies and detection outcomes.
Data Source
AI summary
Machine vision techniques for determining a region of interest (ROI) are disclosed herein. An example implementation includes a computing device for executing an application, the application operable to: (1) capture a first plurality of images over a field of view (FOV); (2) identify, from the first plurality of images, a plurality of regions of interest (ROIs) within the FOV, each of the plurality of ROIs being ranked based on a recurrence frequency of the visual feature within a predetermined proximity to each of the ROIs within the plurality of images; and (3) successively identifying a candidate location for the visual feature within the second image based on a rank of each of the ROIs, until the visual feature is identified in the candidate location.