Date of Publication :7th January 2015

Abstract: The key idea of Adaptive tracking is how to train an online discriminative classifier which can well separate object from its local background. The classifier is incrementally updated using positive and negative samples extracted from the current frame around the detected object location. If the detection is less accurate thereby leading to visual drift. Recently, the multiple instances learning (MIL) based tracker has been proposed to solve these problems to some degree. It puts samples into the positive and negative bags, and then selects some features with an online boosting method via maximizing the bag likelihood function. Finally, the selected features are combined for classification. In MIL tracker, the features are selected by a likelihood function, which can be less informative to tell the target from complex background. Motivated by the active learning method, in this paper we propose an enhanced active feature selection approach which is able to select more informative features than MIL tracker by using the Fisher information criterion to measure the uncertainty of classification model. More specifically, we propose an online boosting feature selection approach via optimizing the Fisher information criterion, which can yield more robust and efficient real-time object tracking performance. Experimental evaluations on challenging sequences demonstrate the efficiency, accuracy and robustness of the proposed tracker in comparison with state-of-the-arts.

Reference :