On-Line Selection of Discriminative Tracking Features

This paper presents 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 on-line feature ranking mechanism based on the two-class variance ratio measure, applied to log likelihood values computed from empirical distributions of object and background pixels with respect to a given feature. This feature ranking 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. This work is supported in part by DARPA/IAO HumanID under ONR contract N00014-00-1-0915, and by DARPA/IPTO MARS contract NBCHC020090. c2003 Carnegie Mellon University This work has been submitted to IEEE ICCV03 ...

• Type: Conference
• Year: 2003
• Where: ICCV
• Authors: Robert T. Collins, Yanxi Liu
• Keywords: Computer Vision, Feature Ranking Mechanism, ICCV 2003, Multiple Feature Spaces, Top-ranked Discriminative Features, University This Work, Variance Ratio Measure