Abstract We propose an exemplar-based tracking framework for human contour tracking. The exemplars, i.e. the contour representatives, are used to construct a contour ensemble. The main task of contour ensemble is to generate contours to fill in the gaps in-between in the test sequences, and to supply the dynamics for updating the target contour by fast contour query. As a result, a normal dynamic Bayesian network is only used to infer the location and the size of the target contour. The effectiveness of the proposed method is tested by many human motion sequences.
Exemplar-Based Human Contour Tracking
Computer Vision – ACCV 2006 ; 4 ; 338-347
Lecture Notes in Computer Science ; 3851 , 4
2006-01-01
10 pages
Article/Chapter (Book)
Electronic Resource
English
Dynamic Bayesian Network , Texture Synthesis , Sequential Monte Carlo , Contour Generation , Contour Tracking Computer Science , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Image Processing and Computer Vision , Artificial Intelligence (incl. Robotics) , Algorithm Analysis and Problem Complexity
Exemplar-Based Human Contour Tracking
British Library Conference Proceedings | 2006
|Viewpoint invariant exemplar-based 3D human tracking
British Library Online Contents | 2006
|Exemplar-based tracking and recognition of arm gestures
IEEE | 2003
|Exemplar-Based Tracking and Recognition of Arm Gestures
British Library Conference Proceedings | 2003
|Object removal by exemplar-based inpainting
IEEE | 2003
|