Robust tracking with per-exemplar support vector machine

The authors extend exemplar representation to the field of tracking and propose a robust tracking algorithm with per-exemplar support vector machine (SVM) classifiers. First, the authors train the simple yet effective exemplar SVM classifier using the target object as the single positive and mining its surroundings as hard negatives. Second, the authors propose an online ensemble tracker, which integrates the useful `key historical templates´ of the target to refine the current template, leading to better discriminative power of tracker and effectively decreasing the risk of drift. Experiments on challenging sequences demonstrate that the tracker performs well in accuracy and robustness, especially under the sequences with strong illumination variation and scale variation, as well as pose change and partial occlusion in the long-time sequence.