Bayesian Pixel Classification for Human Tracking

We present a monocular object tracker, able to detect and track multiple objects in non-controlled environments. Bayesian per-pixel classification is used to build a tracking framework that segments an image into foreground and background objects, based on observations of object appearances and motions. Gaussian mixtures are used to build the color appearance models. The system adapts to changing lighting conditions, handles occlusions, and works in real-time.

[1]  Larry S. Davis,et al.  M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo , 2002, ECCV.

[2]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  Rama Chellappa,et al.  An appearance based approach for human and object tracking , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[4]  Sharath Pankanti,et al.  Appearance models for occlusion handling , 2006, Image Vis. Comput..

[5]  R. Collins,et al.  On-line selection of discriminative tracking features , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[7]  Yanxi Liu,et al.  Online Selection of Discriminative Tracking Features , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Mubarak Shah,et al.  Tracking across multiple cameras with disjoint views , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  James J. Little,et al.  A Boosted Particle Filter: Multitarget Detection and Tracking , 2004, ECCV.

[10]  Luc Van Gool,et al.  An adaptive color-based particle filter , 2003, Image Vis. Comput..