Title :
Visual tracking via geometric particle filtering on the affine group with optimal importance functions
Author :
Junghyun Kwon ; Kyoung Mu Lee ; Park, F.C.
Author_Institution :
Dept. of EECS, Seoul Nat. Univ., Seoul, South Korea
Abstract :
We propose a geometric method for visual tracking, in which the 2-D affine motion of a given object template is estimated in a video sequence by means of coordinate-invariant particle filtering on the 2-D affine group Aff(2). Tracking performance is further enhanced through a geometrically defined optimal importance function, obtained explicitly via Taylor expansion of a principal component analysis based measurement function on Aff(2). The efficiency of our approach to tracking is demonstrated via comparative experiments.
Keywords :
affine transforms; image motion analysis; image sequences; particle filtering (numerical methods); principal component analysis; tracking filters; video signal processing; 2-D affine motion; Taylor expansion; coordinate-invariant particle filtering; geometric method; optimal importance function; principal component analysis; video sequence; visual tracking; Filtering; Gaussian distribution; Motion estimation; Particle measurements; Particle tracking; Predictive models; Principal component analysis; Taylor series; Two dimensional displays; Video sequences;
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
Print_ISBN :
978-1-4244-3992-8
DOI :
10.1109/CVPR.2009.5206501
