The 1st Anti-UAV Workshop & Challenge


June 14th - 19th, 2020 Seattle, WA



Paper Publications

Effect of Annotation Errors on Drone Detection with YOLOv3
Aybora Koksal (Middle East Technical University)*; Kutalmis Ince (Middle East Technical University); Aydin Alatan (Middle East Technical University, Turkey)
The 1st Anti-UAV Workshop & Challenge - CVPR Workshops, 2020


IPG-Net: Image Pyramid Guidance Network for Small Object Detection
Ziming Liu (Beijing Institute of Technology); Guangyu Ryan Gao (Beijing Institute of Technology)*; Lin Sun (Samsung, Standford, HKUST); Li Fang (Beijing Institute of Technology)
The 1st Anti-UAV Workshop & Challenge - CVPR Workshops, 2020


Robust High-speed Siamese Tracker with Template Update Network
LinCan Li (Northeastern University)*; Shuo Yang (Zhejiang University); Zhenyu Lin (Zhejiang University); Tong Jia (Northeastern University)
The 1st Anti-UAV Workshop & Challenge - CVPR Workshops, 2020


Real-time Tracking with Stabilized Frame
ZiXuan Wang ( Beijing University of Posts and Telecommunications)*; Zhicheng Zhao (bupt); Fei Su (Beijing University of Posts and Telecommunications)
The 1st Anti-UAV Workshop & Challenge - CVPR Workshops, 2020


A Real-time Robust Approach for Tracking UAVs in Infrared Videos
Han Wu (Xi'an Jiaotong University); Weiqiang Li (Xi'an Jiaotong University); Wanqi Li (Xi'an Jiaotong University); Guizhong Liu (Xi'an Jiaotong University)*
The 1st Anti-UAV Workshop & Challenge - CVPR Workshops, 2020


Challenge Leaderboard

Rank Team Name Tracking Accuracy
1 xiaobaibai 0.7381
2 zhaoxingjie 0.7346
3 tominute 0.7338
4 banaani 0.7326
5 yukawa 0.7301
6 xjtuwh 0.7233
7 Midkey 0.7120
8 uavdet20 0.7033
9 antiuav2020 0.6786
10 krislhh 0.6394
Note: Please refer to the Evaluate website to obtain detailed definition of tracking accuracy.


Top-3 Award Team Information

Rank Team Name Team Members Organization
🥇 xiaobaibai Chunhui Zhang1,2, Haolin Liu1,2,
Tianyang Xu3, Yong Wang4,5, Shiming Ge1
1 Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
2 University of Chinese Academy of Sciences, Beijing, China
3 Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, UK
4 School of Aeronautics and Astronautics, Sun Yat-Sen University, Guangzhou, China
5 School of Electrical and Computer Science, University of Ottawa, Ottawa, Canada
🥈 zhaoxingjie Xingjie Zhao, Ting Sun Xi’an Jiaotong University, Shaanxi, China
🥉 tominute Linyu Zheng, Bin Yu,
Peigeng Ding, Yingying Chen
Institute of Automation, Chinese Academy of Sciences, Beijing, China


Submit Tracking Results

Please submit your result on codalab.

Our challenge has two stages:

  • test-dev: This dataset is used to test your code config. You can upload 5 times per day.
  • test-challenge: This result will decide your final rank. You can only upload 5 times totally on April 8th-15th

We also provide a baseline tutorial. Please refer to our github.


Participation requirements

The dataset of test-dev is NOT allowed to be used in learning.

Applying pretrained UAV detecter is NOT allowed.

Contestants are encouraged to submit previously published trackers or modified versions of third-party trackers.

The submission description should clearly state the algorithm framework.


Ranking

All teams with successful submissions have a placeholder in the leaderboard, and the results of all teams will be released on May 8th 2020. The winner of the challenge is the team with maximal numbers of accuracy metrics.