Visual tracking on the affine group via geometric particle filtering using optimal importance function

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 coordinateinvariant 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.

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Junghyun Kwon (Seoul National University), Kyoung Mu Lee (Seoul National University), Frank Park (Seoul National University)
• Keywords: Affine Group, Computer Vision, CVPR 2009, Optimal Importance Function, Particle Filtering, Visual Tracking