VisDrone-DET2021: The Vision Meets Drone Object Detection Challenge Results

Yaru Cao, Zhijian He, Lujia Wang, Wenguan Wang, Yixuan Yuan, Dingwen Zhang, Jinglin Zhang, Pengfei Zhu, Luc Van Gool, Junwei Han, Steven Hoi, Qinghua Hu, Ming Liu; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 2847-2854

Object detection on the drone faces a great diversity of challenges such as small object inference, background clutter and wide viewpoint. In contrast to traditional detection problem in computer vision, object detection in bird-like angle can not be transplanted directly from common-in-use methods due to special object texture in sky`s view. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize Vision Meets Drones: A Challenge (VisDrone2021) in conjunction with IEEE International Conference on Computer Vision (ICCV 2021) to promote the developments in the related fields. The collected dataset is formed by 3,190 images, including 1,610 images for training, and 1,580 images for testing. Specifically, teams are required to predict the bounding boxes of objects of ten predefined classes. We received results from many teams using different methods, and this article introduces the methods of the top 10 teams. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: http://www.aiskyeye.com.