VisDrone-VDT2018: The Vision Meets Drone Video Detection and Tracking Challenge Results

Pengfei Zhu, Longyin Wen, Dawei Du, Xiao Bian, Haibin Ling, Qinghua Hu, Haotian Wu, Qinqin Nie, Hao Cheng, Chenfeng Liu, Xiaoyu Liu, Wenya Ma, Lianjie Wang, Arne Schumann, Dan Wang, Diego Ortego, Elena Luna, Emmanouil Michail, Erik Bochinski, Feng Ni, Filiz Bunyak, Gege Zhang, Guna Seetharaman, Guorong Li, Hongyang Yu, Ioannis Kompatsiaris, Jianfei Zhao, Jie Gao, Jose M. Martinez, Juan C. San Miguel, Kannappan Palaniappan, Konstantinos Avgerinakis, Lars Sommer, Martin Lauer, Mengkun Liu, Noor M. Al-Shakarji, Oliver Acatay, Panagiotis Giannakeris, Qijie Zhao, Qinghua Ma, Qingming Huang, Stefanos Vrochidis, Thomas Sikora, Tobias Senst, Wei Song, Wei Tian, Wenhua Zhang, Yanyun Zhao, Yidong Bai, Yinan Wu, Yongtao Wang, Yuxuan Li, Zhaoliang Pi, Zhiming Ma; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0


Drones equipped with cameras have been fast deployed to a wide range of applications, such as agriculture, aerial photography, fast delivery, and surveillance. As the core steps in those applications, video object detection and tracking attracts much research effort in recent years. However, the current video object detection and tracking algorithms are not usually optimal for dealing with video sequences captured by drones, due to various challenges, such as viewpoint change and scales. To promote and track the development of the detection and tracking algorithms with drones, we organized the Vision Meets Drone Video Detection and Tracking (VisDrone-VDT2018) challenge, which is a subtrack of the Vision Meets Drone 2018 challenge workshop in conjunction with the 15th European Conference on Computer Vision (ECCV 2018). Specifically, this workshop challenge consists of two tasks, (1) video object detection, and (2) multi-object tracking. We present a large-scale video object detection and tracking dataset, which consists of 79 video clips with about 1.5 million annotated bounding boxes in 33,366 frames. We also provide rich annotations, including object categories, occlusion, and truncation ratios for better data usage. Being the largest such dataset ever published, the challenge enables extensive evaluation, investigation and tracking the progress of object detection and tracking algorithms on the drone platform. We present the evaluation protocol of the VisDrone-VDT2018 challenge and the results of the algorithms on the benchmark dataset, which are publicly available on the challenge website: We hope the challenge largely boost the research and development in related fields.

Related Material

author = {Zhu, Pengfei and Wen, Longyin and Du, Dawei and Bian, Xiao and Ling, Haibin and Hu, Qinghua and Wu, Haotian and Nie, Qinqin and Cheng, Hao and Liu, Chenfeng and Liu, Xiaoyu and Ma, Wenya and Wang, Lianjie and Schumann, Arne and Wang, Dan and Ortego, Diego and Luna, Elena and Michail, Emmanouil and Bochinski, Erik and Ni, Feng and Bunyak, Filiz and Zhang, Gege and Seetharaman, Guna and Li, Guorong and Yu, Hongyang and Kompatsiaris, Ioannis and Zhao, Jianfei and Gao, Jie and Martinez, Jose M. and San Miguel, Juan C. and Palaniappan, Kannappan and Avgerinakis, Konstantinos and Sommer, Lars and Lauer, Martin and Liu, Mengkun and Al-Shakarji, Noor M. and Acatay, Oliver and Giannakeris, Panagiotis and Zhao, Qijie and Ma, Qinghua and Huang, Qingming and Vrochidis, Stefanos and Sikora, Thomas and Senst, Tobias and Song, Wei and Tian, Wei and Zhang, Wenhua and Zhao, Yanyun and Bai, Yidong and Wu, Yinan and Wang, Yongtao and Li, Yuxuan and Pi, Zhaoliang and Ma, Zhiming},
title = {VisDrone-VDT2018: The Vision Meets Drone Video Detection and Tracking Challenge Results},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}