Abstract: Due to the influence of frequent occlusion, scale variation, boundary effect and other factors, it is often difficult to achieve the desired results in target tracking. At the same time, the traditional feature extraction strategy affects the robustness of target tracking. To address the above problems, we proposed a correlation filter tracking algorithm with spatial regularization and sparse constraints, which utilized the effective fusion of traditional features and deep features to adapt to the changes of the target appearance. Based on the peak side lobe ratio, a judgment was made on whether the target is occluded in the tracking process. If occlusion occurs, sparse constraints are applied to the filter for the improvement of robustness against the occlusion problem. Otherwise, the filter coefficients are adjusted in Gaussian space to suppress the influence of boundary effect. Five sets of standard video sequences in OTB datasets including severe occlusion and scale change, were used to test the tracking performance of the proposed algorithm, and four hot spot algorithms were compared qualitatively and quantitatively. In qualitative analysis, the main challenges of video sequences were compared. In quantitative analysis, the performance of tracking algorithm was compared by center point position error and overlap success rate. Experimental results show that the proposed algorithm is more robust to the above-mentioned challenges. 

Key words:  , target tracking, correlation filtering, deep feature, sparse constraint, space regularization