A robust visual tracking method with Restricted Boltzmann Machines based classifier

摘要

In general, visual trackers employ hand-crafted feature descriptors to track the object, which limits their performance. In this paper, a novel Restricted Boltzmann Machine based Tracker (RBMT) is proposed to enhance the robustness. RBMs are introduced to learn multiple feature descriptors for the different image cues which are transformed from the given images. A data augment method is introduced to online train the RBMs so as to make the learnt feature descriptors specific for different tracked objects. To make the proposed tracker adapted to drastic varying scenes, a feature selection method is also developed to fuse the multiple cues in feature level for the design of appearance-based classifiers. Our experimental results have shown that the proposed tracker can obtain promising performances compared with the other state-of-the-art approaches.