An object tracking algorithm based on optical flow and temporal–spatial context

Image object tracking, as one of the hot spots in computer vision, has made great progress recently. Nevertheless, there has been no algorithm that could show good robustness against all kinds of challenging video scenes. The tracking algorithm of temporal–spatial context effectively took advantage of the information contained in the background and the appearance of the object. By adopting this algorithm, good tracking effects has been achieved. However, such algorithm could easily lead to tracking failure in case of the object moving too fast or the object location changing too much. With Harris corner point adopted as the feature point, this paper corrected the tracking result of the STC tracking algorithm by using the L–K optical flow method as an auxiliary technique. Consequently, better tracking effects were achieved under the premise of preserving the excellent performance of the STC algorithm.