Robust mean shift tracking with improved Background-weighted histogram
Tracking objects in videos using mean shift technique has brought to public attention. In this paper, we developed an improved tracking algorithm based on the mean shift framework. To represent the object model more accurately, the motion direction of the object which was estimated by the local motion filters was employed to weight the histogram. Besides, a wise object template updating strategy was proposed to adapt to the change of the object appearance caused by noise, deformation or occlusion. The experimental results on several real world scenarios shows that our approach has an excellent tracking performance comparing with the background weighted histogram mean shift tracking approach and traditional mean shift tracking method.
object tracking mean shift background-weighted histogram
Liangwei Jiang Rui Huang Nong Sang
National Key Laboratory Science & Technology on Multi-spectral Information Processing Institute for National Key Laboratory Science & Technology on Multi-spectral Information ProcessingInstitute for P
国际会议
桂林
英文
1-8
2011-11-01（万方平台首次上网日期，不代表论文的发表时间）