Time Varying Metric Learning for visual tracking

Traditional tracking-by-detection based methods treat the target and the background as a binary classification problem. This two class classification method suffers from two main drawbacks. Firstly, the learning result may be unreliable when the number of training samples is not large enough. Secondly, the binary classifier tends to drift because of the complex background tracking conditions. In this paper, we propose a new model called Time Varying Metric Learning (TVML) for visual tracking. We adopt the Wishart Process to model the time varying metrics for target features, and apply the Recursive Bayesian Estimation (RBE) framework to learn the metric from the data with "side information contraint". Metric learning with side information is able to omit the clustering of negative samples, which is more preferable in complex background tracking scenarios. The recursive Bayesian model ensures the learned metric is accurate with limited training samples. The experimental results demonstrate the comparable performance of the TVML tracker compared to state-of-the-art methods, especially when there are background clutters. (C) 2016 Elsevier B.V. All rights reserved.