Object contour tracking using multi-feature fusion based particle filter

Abstract

In this paper, a novel object contour tracking framework integrating independent multi-feature fusion object rough location and region-based temporal differencing model is proposed. In our model, the object rough location tracking is realized by color histogram and Harris corner features fusion method in particle filter framework. Thus it can achieve more robust tracking performance in many challenge scenes. And this particle filter framework is based on our previous CamShift guided particle filter [7]. With the rough object location, efficient region-based temporal differencing model is adopted for object contour detection, then this method is faster and more effective compared to active contour models or conventional global temporal differencing models. Moreover, exact contour tracking result can be used to guide the particle propagation of next frame, to enable more efficient particle redistributions and reducing particle degeneration. Experimental results demonstrate that this proposed method is simple but effective in object location and contour tracking.

Publication
2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA)
Xiaofeng Lu
Xiaofeng Lu
PhD Student
Li Song
Li Song
Professor, IEEE Senior Member

Professor, Doctoral Supervisor, the Deputy Director of the Institute of Image Communication and Network Engineering of Shanghai Jiao Tong University, the Double-Appointed Professor of the Institute of Artificial Intelligence and the Collaborative Innovation Center of Future Media Network, the Deputy Secretary-General of the China Video User Experience Alliance and head of the standards group.

Nam Ling
Nam Ling
Professor,IEEE Fellow