VisDrone-MOT2020: The Vision Meets Drone Multiple Object Tracking Challenge Results
| Autor: | Zhaoze Zhao, Longyin Wen, Min Yao, Zhenyu Xu, Jie Han, Wentao Yu, Guna Seetharaman, Ting Sun, Filiz Bunyak, Pengfei Zhu, Xi Wu, Yuehan Yao, Mubarak Shah, Kannappan Palaniappan, Yanyun Zhao, Duo Xu, V. Haritha, Zhipeng Luo, Xingjie Zhao, Guizhong Liu, Xiaopeng Hong, Bin Dong, Yihong Gong, Linu Shine, Zhizhao Duan, P. S. Hrishikesh, Heng Fan, Kaojin Zhu, Arne Schumann, Lars Sommer, Wang Sai, Shengwen Li, Xing Wei, Daniel Stadler, Yuhang He, Dawei Du, Zhen Xie, Junwen Pan, Noor M. Al-Shakarji, Zheng Yang, Qinghua Hu, Haibin Ling, Libo Zhang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: | |
| Zdroj: | Computer Vision – ECCV 2020 Workshops ISBN: 9783030668228 ECCV Workshops (4) |
| DOI: | 10.1007/978-3-030-66823-5_43 |
| Popis: | The Vision Meets Drone (VisDrone2020) Multiple Object Tracking (MOT) is the third annual UAV MOT tracking evaluation activity organized by the VisDrone team, in conjunction with European Conference on Computer Vision (ECCV 2020). The VisDrone-MOT2020 consists of 79 challenging video sequences, including 56 videos (\(\sim \)24K frames) for training, 7 videos (\(\sim \)3K frames) for validation and 17 videos (\(\sim \)6K frames) for evaluation. All frames in these sequences are manually annotated with high-quality bounding boxes. Results of 12 participating MOT algorithms are presented and analyzed in detail. The challenging results, video sequences as well as the evaluation toolkit are made available at http://aiskyeye.com/. By holding VisDrone-MOT2020 challenge, we hope to facilitate future research and applications of MOT algorithms on drone videos. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|