摘要：To solve the problem of the redundant number of training samples in a correlation filter-based tracking algorithm, the training samples were implicitly extended by circular shifts of the given target patches, and all the extended samples were used as negative samples for the fast online learning of the filter. Since all these shifted patches were not true negative samples of the target, the tracking process suffered from boundary effects, especially in challenging situations such as occlusion and background clutter, which can significantly impair the tracking performance of the tracker. Spatial regularization in the SRDCF tracking algorithm is an effective way to mitigate boundary effects, but it comes at the cost of highly increased time complexity, resulting in a very slow tracking speed of the SRDCF algorithm that cannot achieve a real-time tracking effect. To address this issue, we proposed a fast-tracking algorithm based on spatially regularized correlation filters that efficiently optimized the solved filters by replacing the Gauss–Seidel method in the SRDCF algorithm with the alternating direction multiplier method. The problem of slow speed in the SRDCF tracking algorithm improved, and the improved FSRCF algorithm achieved real-time tracking. An adaptive update mechanism was proposed by using the feedback from the high confidence tracking results to avoid model corruption. That is, a robust confidence evaluation criterion was introduced in the model update phase, which combined the maximum response criterion and the average peak correlation energy APCE criterion to determine whether to update the filter, thereby avoiding filter model drift and improving the target tracking accuracy and speed. We conducted extensive experiments on datasets OTB-2015, OTB-2013, UAV123, and TC128, and the experimental results show that the proposed algorithm exhibits a more stable and accurate tracking performance in the presence of occlusion and background clutter during tracking.
