Abstract
During the target tracking process of unmanned aerial vehicles (UAVs), the target may disappear from view or be fully occluded by other objects, resulting in tracking failure. Therefore, determining how to identify tracking failure and re-detect the target is the key to the long-term target tracking of UAVs. Kernelized correlation filter (KCF) has been very popular for its satisfactory speed and accuracy since it was proposed. It is very suitable for UAV target tracking systems with high real-time requirements. However, it cannot detect tracking failure, so it is not suitable for long-term target tracking. Based on the above research, we propose an improved KCF to match long-term target tracking requirements. Firstly, we introduce a confidence mechanism to evaluate the target tracking results to determine the status of target tracking. Secondly, the tracking model update strategy is designed to make the model suffer from less background information interference, thereby improving the robustness of the algorithm. Finally, the Normalized Cross Correlation (NCC) template matching is used to make a regional proposal first, and then the tracking model is used for target re-detection. Then, we successfully apply the algorithm to the UAV system. The system uses binocular cameras to estimate the target position accurately, and we design a control method to keep the target in the UAV’s field of view. Our algorithm has achieved the best results in both short-term and long-term evaluations of experiments on tracking benchmarks, which proves that the algorithm is superior to the baseline algorithm and has quite good performance. Outdoor experiments show that the developed UAV system can achieve long-term, autonomous target tracking.
Highlights
An unmanned aerial vehicle (UAV) refers to an aircraft that is operated by radio remote control equipment and self-provided program control devices without any pilot, or is completely or intermittently operated by an on-board computer
We summarize the problems of the UAV’s long-term target tracking as follows: (1) How can one design a robust tracker which can reasonably respond to changes of the target and the environment and deal with the problem of occlusion and disappearance of the target? (2) How can one judge the position of the target and design a closed-loop control method so that the UAV can track the target continuously? (3) Due to the limited computing ability of onboard computer, how can one ensure that the system can run in real time?
UAV20L is a tracking dataset proposed by Mueller et al [36], which was taken by a low-altitude UAV
Summary
An unmanned aerial vehicle (UAV) refers to an aircraft that is operated by radio remote control equipment and self-provided program control devices without any pilot, or is completely or intermittently operated by an on-board computer. With the advancement of electronic, information, control, sensor technologies and the reduction of manufacturing costs, UAVs have begun to be used in civilian fields and scientific research to solve various problems, such as environmental monitoring [1], search and rescue [2], transportation [3], etc In these applications, UAVs are required to track a target autonomously for a long time. We evaluated our tracker reasonably; (2) we use binocular camera to accurately estimate the position of targets and designed a control strategy to keep the target in the UAV’s field of view and keep a certain distance from the UAV; (3) we propose a framework that makes the entire system integrated on Jetson TX2 and mounted on DJI M100 and successfully conduct outdoor experiments, verifying the feasibility of the framework.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
