Tracking and Recognizing Actions at a Distance

This paper presents a template-based algorithm to track and recognize athlete’s actions in an integrated system using only visual information. Usually the two elements of tracking and action recognition are treated separately. In contrast, our algorithm emphasizes that tracking and action recognition can be tightly coupled into a single framework, where tracking assists action recognition and vice versa. Moreover, this paper proposes to represent the athletes by the grids of Histograms of Oriented Gradient (HOG) descriptor. The using of the HOG descriptor not only improves the robustness of the tracker, but also centers the figure in the tracking region. Therefore, no further stabilization techniques are needed. Empirical results on hockey and soccer sequences show the effectiveness of this algorithm.