Adaptive Multiple Component Metric Learning for Robust Visual Tracking

In this paper, we present a new robust visual tracking approach that incorporates an adaptive metric learning in a multiple components framework. Using a similar overall approach to other state-of-the-art tracking methods, which pose object tracking as a binary classification problem, we firstly employ a new feature selection mechanism based on adaptive metric learning for constructing a discriminative target appearance model and then propose a scheme to update the appearance model in a Multiple Component Learning boosting manner, which automatically learns individual component classifiers and combines these into an overall classifier. Experiments on several challenging benchmark video sequences demonstrate the effectiveness and robustness of our proposed method.