Visual tracking of a moving object via the soft cosine measure

In this paper, we propose a Local Soft Similarity based on Soft Cosine Measure (L3SCM) and then we incorporate it into visual tracking framework. Firstly, we present the soft cosine measure that measures the soft similarity between two vectors of features by taking into consideration similarities of pairs of features. Secondly, we apply this soft similarity in the observation model component of the proposed tracker to measure the local similarities between the template of the tracked target and the sampled candidates. Finally, in order to improve the robustness of the proposed tracker, we integrate a simple scheme to update the target template throughout the tracking process. Experimental results on several challenging image sequences illustrate that the proposed method performs better against several state-of-the-art trackers.