Gaussian-based adaptive frame skipping for visual object tracking

Visual object tracking is a basic computer vision problem, which has been greatly developed in recent years. Although the accuracy of object tracking algorithms has been improved, the efficiency of most trackers is hard to meet practical requirements, especially for devices with limited computational power. To improve visual object tracking efficiency with no or little loss of accuracy, a frame skipping method is proposed for correlation filter-based trackers, which includes an adaptive tracking-skipping algorithm and Gaussian-based movement prediction. According to the movement state of objects in the previous frames, the position of objects in the next frame can be predicted, and whether or not the tracking process should be skipped is determined by the predicted position. Experiments are conducted on both practical video surveillance and well-known public data sets to evaluate the proposed method. Experimental results show that the proposed method can almost double the tracking efficiency of correlation filter-based trackers with no or little accuracy loss.