People Counting System Self-Verification via Area Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated people counting systems lack reliable and cost-effective methods for verifying accuracy, as human verification is impractical and additional automated systems are expensive and introduce infrastructure issues, making it difficult to detect counting errors over time.
Innovation Solution
An automated method and apparatus that processes digitized images to detect moving objects crossing a defined area, accumulating counts of objects entering and leaving, and computes an accuracy measure based on these counts, allowing for continuous and automated error detection without additional hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If human counters are used to verify counting accuracy, then verification can be performed, but human fatigue and high costs make it impractical for ongoing accuracy monitoring
Solution Approach 1:
The counting system performs self-verification by using its own counting capabilities to monitor its accuracy. The system divides the monitored area into multiple sub-areas, counts objects in each sub-area separately, and verifies overall accuracy by comparing the sum of sub-area counts with the total area count, eliminating the need for external human verification.
Solution Approach 2:
The monitored area is segmented into multiple non-overlapping sub-areas, each with its own counter. This segmentation allows the system to verify accuracy by comparing aggregated sub-area counts with the total count, enabling ongoing automated verification without human intervention.
2Measurement precision
If additional automated counting systems are deployed to verify accuracy, then consistent verification is achieved, but cost and infrastructure requirements increase significantly
Solution Approach 1:
The existing counting system is made multi-functional by enabling it to perform both its primary counting function and its own accuracy verification function. The same processor and counting logic are used to count objects in sub-areas and verify the accuracy of total counts, eliminating the need for separate verification hardware.
Solution Approach 2:
The system verifies its own accuracy using its existing infrastructure. The processor that counts objects also performs the verification by comparing sub-area counts with total counts, making the system self-sufficient and avoiding additional hardware investments.
3Measurement precision
If traditional verification methods are used, then some accuracy data can be obtained, but it is difficult to correlate data and identify when errors occurred
Solution Approach 1:
By dividing the monitoring area into multiple sub-areas with individual counters, the system can identify which specific sub-area is causing counting discrepancies. This segmentation preserves location information and enables precise error identification without losing spatial data.
Solution Approach 2:
The system continuously compares the sum of sub-area counts with the total area count and provides feedback when discrepancies are detected. This real-time feedback mechanism identifies errors as they occur, preserving timing information and enabling immediate error detection and correction.
Data Source
AI summary
A system for counting a number of people or other moving objects entering or leaving a space has a camera which provides an image of an entrance to the space. A data processor identifies moving objects in the image. The data processor is configured to count people or other objects which enter or leave an area within the image for two or more segments of a boundary of the area. Accuracy of the counting system can be monitored by comparing the counts for the different segments.