关键词: 无人机, 目标跟踪, 孪生网络, Kalman滤波, 重定位机制, 追踪状态检测

Abstract: Aiming at the target tracking process of unmanned aerial vehicle (UAV) for air-ground targets, which occurs when the target leaves the field of view, the target is occluded, and the existence of similar target interference leads to tracking failure, a relocation mechanism based on the tracking status detection and Kalman filter is proposed, which is combined with the fully convolutional Siamese network (siamfc) tracker. In this paper, an air-ground target is taken as the object to be tracked, and an unmanned aerial vehicle (UAV) is taken as the tracker to track the air-ground target. First, the detection mechanism based on the selection mechanism for double peaks, changing rate of average peak correlation energy, changing rate of maximum response value, and changing rate of peak to sidelobe ratio detects whether the current track-ing status is abnormal or not to determine whether the tracking results of the siamfc satisfy the requirement of being an observation. Secondly, Kalman filter utilizes a priori information of the target motion to predict and update the tracking result. When the tracking status is abnormal, it can correct and adjust the tracking result in time. We use the LaSOT video dataset to train the network. Real-time object tracking tests and comparison experiments were operated on UAV123 aerial dataset and the customized dataset with UAV as the target. The experimental results show that the algorithm has an accuracy and success rate of 66.0% and 47.4% (62fps) on UAV123, and 72.0% and 58.6% (55fps) on the customized dataset with UAV as the target, which meets the real-time requirements of UAV object tracking and the tracking results are better than most trackers. The algorithm accomplishes effective target tracking with both UAVs as trackers and tracked objects, and has an enhanced ability to cope with challenging scenarios such as the target leaving the field of view, partial or total occlusion, and similar target interference. Meanwhile, the algorithm has good generalization.

Key words: UAV, Object Tracking, Siamese Network, Kalman Filter, Relocation Mechanism, Tracking Status Detection