Tracking of Moving Objects With Regeneration of Object Feature Points

Abstract

This paper concerns moving object tracking in the videos, based on sparse optical flow technique. Current optical flow tracking methods suffer from feature points loss. We extended an existing sparse optical flow tracking method with a new function for automatic feature points' recovery that uses biological regeneration principle. Besides, we improved the tracking method to deal with object rotation and scaling transformations. We applied the improved tracking method to a real video and noticed acceptable tracking performance. Our experiment showed that the proposed tracking method with feature points' recovery provides higher tracking accuracy than the original tracking method without feature points recovery when the moving object is partially occluded by an obstacle.