A Real-Time Anti-Distractor Infrared UAV Tracker With Channel Feature Refinement Module

Houzhang Fang, Xiaolin Wang, Zikai Liao, Yi Chang, Luxin Yan; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 1240-1248

The unmanned aerial vehicles (UAVs) have been widely used in various application fields, yet unauthorized use of UAVs raises great threats for restricted areas and public security. Therefore, it is urgently necessary to develop a practical anti-UAV target tracking technique. In this paper, we propose a real-time anti-distractor infrared UAV tracker for infrared anti-UAV tasks, which employs a global real-time perception mechanism to find candidate targets, then utilizes spatial-temporal information to obtain the real UAV target. Moreover, we integrate a channel feature refinement module into multi-scale feature fusion to better enhance the representation of the finer features of the UAV targets channel-wisely, thus improving the tracking performance. We test the performance of the proposed method and the other competitive ones on the constructed UAV dataset from ourselves, and eventually verify the validity of the proposed method as the best performing method with a better balance between tracking accuracy and speed.