Spatiotemporal regularization correlation filter with response feedback

摘要

Most existing trackers based on correlation filtering try to introduce different regularizationitems to improve the learning process of the tracking object. However, the parametersof the corresponding regularization items need to be adjusted dynamically to meet the correspondingtracking process. The regularization parameters are often fixed, so they cannot beupdated for more accurate tracking.We propose a method to adaptively adjust the spatiotemporalregularization parameters during the tracking process. We make use of the important correlationbetween the response map and tracking quality in the tracking process of correlation filteringand introduce the confidence description index of the response map to optimize the spatiotemporalregularization parameters, so the training of correlation filtering can focus on the part withhigh confidence. In this way, the overfitting situation in training is reduced, and the accuracy androbustness of the tracker are enhanced. In performance evaluation experiments on the OTB2015and DTB70 datasets, our algorithm outperforms the other comparative algorithms in terms oftracking success rate and distance accuracy, especially in complex scenarios, such as illuminationvariation, background clutter, out-of-view, and low resolution.