DocumentCode :
1659033
Title :
Distance Map of Various Weights: A new feature for adaptive object tracking
Author :
Lin Ma ; Junliang Xing ; Xiaoqin Zhang ; Weiming Hu
Author_Institution :
Inst. of Autom., Beijing, China
fYear :
2013
Firstpage :
1778
Lastpage :
1782
Abstract :
In this paper, we propose a new feature, Distance Map of Various Weights (DMVW) based on distances between rows´ textures, to perform tracking. The proposed new feature provides an effective object appearance model which is both illumination-invariant and robust to occlusion. We also develop a 2D PCA based method to effectively evaluate the new feature. We demonstrate the validity of the rows´ or column´s weights in computing 2D PCA subspaces. To balance the importance of local and global information, we define a coefficient to revise the locality extent of the proposed feature. A new method based on entropy of candidate state evaluation is proposed to select the most discriminative coefficient. Experimental results on challenging video sequences demonstrated the effectiveness of our method.
Keywords :
computer graphics; image sequences; image texture; principal component analysis; 2D PCA based method; DMVW; adaptive object tracking; candidate state evaluation entropy; distance map of various weights; object appearance model; occlusion; video sequences; Abstracts; 2D PCA; particle filter; tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
ISSN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2013.6637958
Filename :
6637958
Link To Document :
بازگشت