Abstract

Successful multi-target tracking requires locating the tar- gets and labeling their identities. This mission becomes significantly more challenging when many targets frequently interact with each other (present partial or complete occlusions). This paper presents an on-line supervised learning based method for tracking multiple interacting tar- gets. When the targets do not interact with each other, multiple in- dependent trackers are employed for training a classifier for each target. When the targets are in close proximity or present occlusions, the learned classifiers are used to assist in tracking. The tracking and learning sup- plement each other in the proposed method, which not only deals with tough problems encountered in multi-target tracking, but also ensures the entire process to be completely on-line. Various evaluations have demonstrated that this method performs better than previous methods when the interactions occur, and can maintain the correct tracking under various complex tracking situations, including crossovers, collisions and occlusions.