UAVDT Benchmark
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
Dawei Du, Yuankai Qi, Hongyang Yu, Yifan Yang, Kaiwen Duan, Guorong Li, Weigang Zhang, Qingming Huang, Qi Tian
With the advantage of high mobility, Unmanned Aerial Vehicles (UAVs) are used to fuel numerous important applications in com-puter vision, delivering more e ciency and convenience than surveillance cameras with fixed camera angle, scale and view. However, very limited UAV datasets are proposed, and they focus only on a specific task such as visual tracking or object detection in relatively constrained scenar-ios. Consequently, it is of great importance to develop an unconstrained UAV benchmark to boost related researches. In this paper, we construct a new UAV benchmark focusing on complex scenarios with new level challenges. Selected from 10 hours raw videos, about 80; 000 represen-tative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e.g., weather condition, fying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking. Then, a detailed quantitative study is performed using most re-cent state-of-the-art algorithms for each task. Experimental results show that the current state-of-the-art methods perform relative worse on our dataset, due to the new challenges appeared in UAV based real scenes, e.g., high density, small object, and camera motion. To our knowledge, our work is the rst time to explore such issues in unconstrained scenes comprehensively.
Downloads:
UAVDT-Benchmark-M
Google Drive: [dataset] [DET/MOT toolkit] [Attributes]
[R-FCN-detections] [RON-detections] [SSD-detections] [FRCNN-detections] [Readme]
Baidu Yunpan: [dataset] (uwn8) [DET/MOT toolkit] (ilxx) [Attributes] (t9d3)
UAVDT-Benchmark-S
Google Drive: [dataset] [SOT toolkit]
Baidu Yunpan: [dataset] (wfww) [SOT toolkit] (4bkf)
If it said the page of Baidu Yunpan was not avaliable, please refresh the website and you will see the data.
Citations
If you use the dataset, our results or the source code, please cite our paper:
• Dawei Du, Yuankai Qi, Hongyang Yu, Yifan Yang, Kaiwen Duan, Guorong Li, Weigang Zhang, Qingming Huang, Qi Tian, " The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking", European Conference on Computer Vision (ECCV), 2018.