Long-Term Target Tracking for UAV Based on Correlation Filter

During UAV target tracking, there still exist some issues such as severe deformation, scale variance, occlusion and even fast motion. In this paper, we propose a more stable, real-time and long-term target tracking algorithm based on correlation filter for these problems. Our proposed tracker mainly included the movement and scale transformation module, which can achieves the precise area of target by combining different scale transformation based on multiple position points. In addition, we exploit the keypoint-based method to solve the redetection issue caused by target disappearance in the UAV long-term tracking process, which ensure stability of the entire system. In this paper, we verify our algorithm on the representative UAV data set called UAV123. The experimental results show that our tracker performs superiorly against several traditional methods at speed of 26 frames per second during tracking.