Non-rigid object tracking with elastic structure of local patches and hierarchical sampling
Kwang Moo Yi, Soo Wan Kim, Hawook Jeong, Songhwai Oh, Jin Young Choi · 2010
To solve the problem of real-time object tracking under partial occlusions and non-rigid deformations, we propose a tracking method based on sequential Bayesian inference. The proposed method is mainly consisted of two parts: (1) modeling the target object using elastic structure of local patches for robust performance; and (2) efficient hierarchical sampling method to obtain an acceptable solution in real-time. The elastic structure of local patches allows the proposed method to handle partial occlusions and non-rigid deformations through the relationship among neighboring patches. The proposed hierarchical sampling method generate samples from the region where the posterior is concentrated to reduce computation time. The method is extensively tested on a number of challenging image sequences with occlusion and non-rigid deformation, demonstrating its real-time capability and robustness under different situations.