UAV Chasing Based on YOLOv3 and Object Tracker for Counter UAV Systems

In this paper, we propose a vision-based unmanned aerial vehicle (UAV) chasing system that can be embedded in a pursuer UAV (pUAV) to protect from attacks by an evader UAV (eUAV). The proposed UAV chasing system consists of two parts: UAV tracking and control signal generation. By combining a deep learning-based object detector, you only look once version three (YOLOv3), and existing object trackers, the proposed UAV tracking algorithm can improve the tracking performance of pUAV within affordable computational complexity. The control signals of the pUAV are generated by utilizing the predicted bounding box area of the eUAV and the proportional-derivative control method. Various combinations of YOLOv3 and object trackers were examined and compared using the object tracking benchmark performance criteria. From the evaluation results, the UAV tracking algorithm with the highest performance is selected, which achieves average success and precision rates for object tracking that are 2.86% and 5.61% higher than YOLOv3, respectively. In addition, the field test verifies that the proposed UAV chasing system outperforms the YOLOv3 system in terms of bounding box misalignment (33% accuracy improvement) and computational complexity (71% reduction).