Long-term Target Tracking Based on Template Updating and Redetection

Abstract To address the issue of targets frequently disappearing and reappearing in long-term tracking scenarios due to occlusion and being out of view, we have developed a long-term target tracking algorithm based on template updating and redetection (LTUSiam). Firstly, on the basis of the basic tracker SiamRPN, a three-level cascade gated cycle unit is introduced to assess the state of the target and select the right time to adopt the template update network to adapt the update template information. Secondly, a re-detection algorithm based on template matching is proposed. The candidate region extraction module is utilized to adjust the target's position and size in the basic tracker, and the evaluation score sequence is used to judge the target loss to determine the tracking state of the next frame. Experiments show that LTUSiam achieves 28 frames per second on VOT2018_LT dataset, achieving good results in real-time tracking, and 0.644 performance on F-score, which has better robustness in handling the problem of target loss recurrence, and effectively improves the performance of long-term tracking.