Title :
Tri-tracking method for robust object tracking
Author :
Zhang, R.-J. ; Lu, Hou-Cheng ; Jia, C.-H. ; Chen, Yi-Wen
Author_Institution :
Dept. of Electron. Eng., Dalian Univ. of Technol., Dalian
Abstract :
A novel tri-tracking method for tracking objects is proposed. The tracker trains three support vector machines with labelled frames, in which an object is represented using three independent feature histograms. Based on the confidence map created by each classifier, the object position is given by the mean shift. Experiments on several video sequences show the robustness and accuracy of the proposed method.
Keywords :
image sequences; object detection; optical tracking; statistical analysis; support vector machines; video signal processing; confidence map; feature histogram; mean shift; object classifier; object position; object tracking; support vector machine; tritracking; video sequence;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20082412
