Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
The Bayesian filtering for recursive state estimation and the shape-based matching methods are two of the most commonly used approaches for target tracking. The Multiple Hypothesi...
This paper presents the application of a kernel particle filter for 3D body tracking in a video stream acquired from a single uncalibrated camera. Using intensity-based and color...
This work introduces a new pattern recognition model for segmenting and tracking lip contours in video sequences. We formulate the problem as a general nonrigid object tracking me...
Robust real-time tracking of non-rigid objects in a dynamic environment is a challenging task. Among various cues in tracking, color can provide an efficient visual cue for this t...