Beyond semisupervised tracking: Tracking should be as simple as detection, but not simpler than recognition

We present a multiple classifier system for model-free tracking. The tasks of detection (finding the object of inter-est), recognition (distinguishing similar objects in a scene), and tracking (retrieving the object to be tracked) are split into separate classifiers in the spirit of simplifying each classification task. The supervised and semi-supervised classifiers are carefully trained on-line in order to increase adaptivity while limiting accumulation of errors, i.e. drift-ing. In the experiments, we demonstrate real-time tracking on several challenging sequences, including multi-object tracking of faces, humans, and other objects. We outper-form other on-line tracking methods especially in case of occlusions and presence of similar objects. 1