Context-driven model switching for visual tracking

Abstract A major challenge for real-world object tracking is the dynamic nature of the environmental conditions with respect to illumination, motion, visibility, etc. For such an environment which may experience drastic changes at any time, integration of multiple and complementary cues promises to increase robustness of visual tracking. Nevertheless, one has to expect that false positive tracking will occur. In order to be able to recover from such tracking failure this paper introduces a novel method for automatically choosing the object model which best fits the current context based on information-theoretic concepts. In order to validate the effectiveness of the proposed model switching, it is integrated into a multi-cue face tracking system and experimentally evaluated.