VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results

Guanlin Chen, Wenguan Wang, Zhijian He, Lujia 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. 2839-2846

Abstract

The Vision Meets Drone (VisDrone2021) Multiple Object Tracking (MOT) is the forth annual activity organizedby the VisDrone team focusing on evaluating UAV MOT tracking algorithms. It is held in conjunction with the International Conference on Computer Vision (ICCV 2021).The VisDrone-MOT2021 provides 96 challenging video sequences, including 56 sequences ( 24K frames) for train-ing , 7 sequences ( 3K frames) for validation and 33 sequences ( 13K frames) for testing. Each frame in the sequences are manually annotated with bounding boxes of different categories of objects. Additionally, occlusion ratio and truncation ratio are provided as extra useful annotations. The results of 8 state-of-the-art MOT algorithmsare presented and reported in detail. We hope to facilitate future research and applications in the field of UAV vision by organizing VisDrone-MOT2021 challenge. More information about the challenge can be found at http://www.aiskyeye.com/. Key words: VisDrone, multi-object tracking, drone, challenge, benchmark

Related Material

[pdf]
[bibtex]
@InProceedings{Chen_2021_ICCV, author = {Chen, Guanlin and Wang, Wenguan and He, Zhijian and Wang, Lujia and Yuan, Yixuan and Zhang, Dingwen and Zhang, Jinglin and Zhu, Pengfei and Van Gool, Luc and Han, Junwei and Hoi, Steven and Hu, Qinghua and Liu, Ming}, title = {VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2839-2846} }