Static Occlusion Detection Using Accumulator Arrays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video-based object tracking systems fail to effectively handle static occlusions, leading to tracking failures in surveillance and traffic monitoring applications, as they lack the ability to accurately locate and account for pixels obstructed by permanent or semi-permanent occlusions.
Innovation Solution
A computer-implemented method and system that automatically identifies pixels corresponding to static occlusions by monitoring the motion of objects over time using an accumulator array, initializing a foreground accumulator array, segmenting and updating it with foreground information, and creating a static occlusion mask to label pixels associated with occlusions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional tracking algorithms are used without occlusion detection, then the system is simpler and faster, but tracking accuracy deteriorates due to static occlusions
Solution Approach 1:
The system performs preliminary action by detecting and mapping static occlusions before tracking operations begin. The occlusion detection process creates a spatial map of occluded regions that is then used by the tracking algorithm to avoid these areas, preventing tracking failures rather than recovering from them.
Solution Approach 2:
The occlusion detection system acts as an intermediary between the camera and the tracking algorithm. It provides additional information about occluded regions that the tracking algorithm cannot obtain on its own, enabling the tracker to make informed decisions about where to search for target objects.
2Extent of automation
If manual occlusion mapping is used, then occlusion location precision is high, but automation level is low requiring manual intervention
Solution Approach 1:
The system performs self-service by automatically detecting and mapping occlusions without requiring manual intervention. The algorithm processes video frames, identifies static occluded regions, and generates an occlusion map autonomously, making the system fully automated while maintaining detection accuracy.
3Productivity
If frame-by-frame feature matching is performed across the entire ROI, then tracking robustness is high, but computational time increases significantly
Solution Approach 1:
The system applies segmentation by dividing the region of interest into occluded and non-occluded regions based on the detected occlusion map. The tracking algorithm then only performs feature matching in the non-occluded regions, significantly reducing the search space and computational requirements while maintaining tracking robustness.
Solution Approach 2:
The system applies local quality by concentrating computational resources only where needed - in the non-occluded regions of the image. Instead of uniformly processing the entire ROI, the algorithm adapts its search effort to the local occlusion characteristics, improving efficiency without sacrificing tracking reliability.
Data Source
AI summary
This disclosure provides a method and system to locate/detect static occlusions associated with an image captured scene including a tracked object. According to an exemplary method, static occlusions are automatically located by monitoring the motion of single or multiple objects in a scene over time and with the use of an associated accumulator array.