Multi‐target tracking by enhancing the kernelised correlation filter‐based tracker

Abstract

A new tracking method based on the kernelised correlation filter (KCF) method is proposed. The tracker improves KCF-based trackers by adding seven proposed components, namely, the motion model, background subtraction, occlusion handling, hijacking handling, object proposal, bounding box modification, and object re-detection. With these components, the tracker robustly tracks multiple targets despite severe occlusion, rapid motion, and the presence of other objects with similar appearance. The visual tracking performance is evaluated by using challenging basketball game videos. Experiments demonstrate that the tracker outperforms the original KCF tracker and other state-of-the-art tracking methods.

DeepPlayer-Track: Player and Referee Tracking With Jersey Color Recognition in Soccer

“…Their technique is simple and effective: an individual correlation filter is added to each item independently while effectively maintaining the processing speed advantage. For example, as compared to representative approaches specifically developed for multiple object tracking [28], textcolorredthe kernelized correlation filter-based approach [26] worked quickly and produced comparable results. Nonetheless, the uncertainty created by extreme occlusions between players and complex motion patterns seen in soccer games continues to impact most approaches.…”

Basketball Tracking using Mean Shift Algorithm

“…Along with it, for every frame ball detection had been mentioned. J. Kwon et al [11] had presented the KCF method which was for tracking purpose. The KCF-based tracker had enhanced by adopting the components.…”