Structural sparse representation-based semi-supervised learning and edge detection proposal for visual tracking

In discriminative tracking, lots of tracking methods easily suffer from changes of pose, illumination and occlusion. To deal with this problem, we propose a novel object tracking method using structural sparse representation-based semi-supervised learning and edge detection. First, the object appearance model is constructed by extracting sparse code features on different layers to exploit local information and holistic information. To utilize unlabelled samples information, the semi-supervised learning is introduced and a classifier is trained which is used to measure candidates. In addition, an auxiliary positive sample set is maintained to improve the performance of the classifier. We subsequently adopt an edge detection to alleviate the error accumulation based on the ranking results from the learned classifier. Finally, the proposed method is implemented under the Bayesian inference framework. Both the proposed tracker and several current trackers are tested on some challenging videos, where the target objects undergo pose change, illumination and occlusion. The experimental results demonstrate that the proposed tracker outperforms the other state-of-the-art methods in terms of effectiveness and robustness.