Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking
This work addresses the need for better surveillance and monitoring of UAVs, which is crucial for security and operational applications, but it is incremental as it primarily provides a new dataset and a method for an existing task.
The authors tackled the problem of tracking unmanned aerial vehicles (UAVs) by introducing a large multi-modal dataset called Anti-UAV with over 300 video pairs and 580k annotated bounding boxes, and they proposed a dual-flow semantic consistency method that effectively improves tracker performance.
Unmanned Aerial Vehicle (UAV) offers lots of applications in both commerce and recreation. With this, monitoring the operation status of UAVs is crucially important. In this work, we consider the task of tracking UAVs, providing rich information such as location and trajectory. To facilitate research on this topic, we propose a dataset, Anti-UAV, with more than 300 video pairs containing over 580k manually annotated bounding boxes. The releasing of such a large-scale dataset could be a useful initial step in research of tracking UAVs. Furthermore, the advancement of addressing research challenges in Anti-UAV can help the design of anti-UAV systems, leading to better surveillance of UAVs. Besides, a novel approach named dual-flow semantic consistency (DFSC) is proposed for UAV tracking. Modulated by the semantic flow across video sequences, the tracker learns more robust class-level semantic information and obtains more discriminative instance-level features. Experimental results demonstrate that Anti-UAV is very challenging, and the proposed method can effectively improve the tracker's performance. The Anti-UAV benchmark and the code of the proposed approach will be publicly available at https://github.com/ucas-vg/Anti-UAV.