Using spatial overlap ratio of independent classifiers for likelihood map fusion in mean-shift tracking

We combine the outputs of independent classifiers for mean-shift tracking within the likelihood map fusion framework and introduce a novel likelihood fusion technique that directly employs the tracking confidences of likelihood maps which are generated by different binary classifiers. Our proposed measure tries to compensate drifting that may be caused by each likelihood map using their independent tracking results. We present results obtained with the proposed fusion approach using two different classifiers, where one models the tracked object and one models the background. The results show superior performance of the proposed fusion technique as compared to the others. We further discuss how the proposed likelihood map fusion approach can be generalized to any number and any kind of likelihood maps.