Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image fea...
Leonid Taycher, John W. Fisher III, Trevor Darrell
We describe a general algorithm for identifying an arbitrary pose of an articulated subject with low density feature points. The algorithm aims to establish a one-to-one correspon...
In this paper, we present a method using pixel-level information, local region-level information and global-level information to remove shadow. At the pixel-level, we employ GMM t...
Zhou Liu, Kaiqi Huang, Tieniu Tan, Liangsheng Wang
Most motion-based tracking algorithms assume that objects undergo rigid motion, which is most likely disobeyed in real world. In this paper, we present a novel motionbased trackin...