On-line selection of discriminative tracking features

We present a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. We develop an online feature selection mechanism based on the two-class variance ratio measure, applied to log likelihood distributions computed with respect to a given feature from samples of object and background pixels. This feature selection mechanism is embedded in a tracking system that adaptively selects the top-ranked discriminative features for tracking. Examples are presented to illustrate how the method adapts to changing appearances of both tracked object and scene background.

[1]  Godfried T. Toussaint,et al.  Note on optimal selection of independent binary-valued features for pattern recognition (Corresp.) , 1971, IEEE Trans. Inf. Theory.

[2]  Gary Bradski,et al.  Computer Vision Face Tracking For Use in a Perceptual User Interface , 1998 .

[3]  P. Anandan,et al.  A Unified Approach to Moving Object Detection in 2D and 3D Scenes , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Francis Quek,et al.  Comparison of five color models in skin pixel classification , 1999, Proceedings International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems. In Conjunction with ICCV'99 (Cat. No.PR00378).

[5]  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).

[6]  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).

[7]  Pradeep K. Khosla,et al.  Probabilistic Adaptive Agent Based System for Dynamic State Estimation using Multiple Visual Cues , 2001, ISRR.

[8]  Helman Stern,et al.  Adaptive color space switching for face tracking in multi-colored lighting environments , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[9]  Yanxi Liu,et al.  Facial asymmetry quantification for expression invariant human identification , 2003, Comput. Vis. Image Underst..

[10]  Yanxi Liu,et al.  Human Identi cation versus Expression Classi cation via Bagging on Facial Asymmetry , 2003 .

[11]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.