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; Andrea Sciarrone; Chao Sun; Chiara Garibotto; Duong Nguyen Ngoc Tran; Fabio Lavagetto; Halar Haleem; Hakki Motorcu; Hasan F. Ates; Huy Hung Nguyen; Hyung Joon Jeon; Igor Bisio; Jae Wook Jeon; Jiahao Li; Long Hoang Pham; Moongu Jeon; Qianyu Feng; Shengwen Li; Tai Huu Phuong Tran; Xiao Pan; Young Min Song; Yuehan Yao; Yunhao Du; Zhenyu Xu; Zhipeng Luo

doi:10.1109/ICCVW54120.2021.00318

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, Andrea Sciarrone, Chao Sun, Chiara Garibotto, Duong Nguyen Ngoc Tran, Fabio Lavagetto, Halar Haleem, Hakki MotorcuHasan F. Ates, Huy Hung Nguyen, Hyung Joon Jeon, Igor Bisio, Jae Wook Jeon, Jiahao Li, Long Hoang Pham, Moongu Jeon, Qianyu Feng, Shengwen Li, Tai Huu Phuong Tran, Xiao Pan, Young Min Song, Yuehan Yao, Yunhao Du, Zhenyu Xu, Zhipeng Luo

School of Automation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

34 Scopus citations

Abstract

Vision Meets Drone: Multiple Object Tracking (VisDrone-MOT2021) challenge - the forth annual activity organized by the VisDrone team - focuses on benchmarking UAV MOT algorithms in realistic challenging environments. It is held in conjunction with ICCV 2021. VisDrone-MOT2021 contains 96 video sequences in total, including 56 sequences (~24K frames) for training, 7 sequences (~3K frames) for validation and 33 sequences (~13K frames) for testing. Bounding-box annotations for novel object categories are provided every frame and temporally consistent instance IDs are also given. Additionally, occlusion ratio and truncation ratio are provided as extra useful annotations. The results of eight state-of-the-art MOT algorithms are reported and discussed. We hope that our VisDrone-MOT2021 challenge will facilitate future research and applications in the field of UAV vision. The website of our challenge can be found at http://www.aiskyeye.com/.

Original language	English
Title of host publication	Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2839-2846
Number of pages	8
ISBN (Electronic)	9781665401913
DOIs	https://doi.org/10.1109/ICCVW54120.2021.00318
State	Published - 2021
Event	18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 - Virtual, Online, Canada Duration: 11 Oct 2021 → 17 Oct 2021

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
Volume	2021-October
ISSN (Print)	1550-5499

Conference

Conference	18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Country/Territory	Canada
City	Virtual, Online
Period	11/10/21 → 17/10/21

Keywords

Benchmark
Challenge
Drone
Multi-object tracking
VisDrone

Access to Document

10.1109/ICCVW54120.2021.00318

Cite this

Chen, G., Wang, W., He, Z., Wang, L., Yuan, Y., Zhang, D., Zhang, J., Zhu, P., Van Gool, L., Han, J., Hoi, S., Hu, Q., Liu, M., Sciarrone, A., Sun, C., Garibotto, C., Tran, D. N. N., Lavagetto, F., Haleem, H., ... Luo, Z. (2021). VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results. In Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 (pp. 2839-2846). (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2021-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW54120.2021.00318

Chen, Guanlin ; Wang, Wenguan ; He, Zhijian et al. / VisDrone-MOT2021 : The Vision Meets Drone Multiple Object Tracking Challenge Results. Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 2839-2846 (Proceedings of the IEEE International Conference on Computer Vision).

@inproceedings{8f3d6f80ce724d6598860a9e84c26037,

title = "VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results",

abstract = "Vision Meets Drone: Multiple Object Tracking (VisDrone-MOT2021) challenge - the forth annual activity organized by the VisDrone team - focuses on benchmarking UAV MOT algorithms in realistic challenging environments. It is held in conjunction with ICCV 2021. VisDrone-MOT2021 contains 96 video sequences in total, including 56 sequences (~24K frames) for training, 7 sequences (~3K frames) for validation and 33 sequences (~13K frames) for testing. Bounding-box annotations for novel object categories are provided every frame and temporally consistent instance IDs are also given. Additionally, occlusion ratio and truncation ratio are provided as extra useful annotations. The results of eight state-of-the-art MOT algorithms are reported and discussed. We hope that our VisDrone-MOT2021 challenge will facilitate future research and applications in the field of UAV vision. The website of our challenge can be found at http://www.aiskyeye.com/.",

keywords = "Benchmark, Challenge, Drone, Multi-object tracking, VisDrone",

author = "Guanlin Chen and Wenguan Wang and Zhijian He and Lujia Wang and Yixuan Yuan and Dingwen Zhang and Jinglin Zhang and Pengfei Zhu and {Van Gool}, Luc and Junwei Han and Steven Hoi and Qinghua Hu and Ming Liu and Andrea Sciarrone and Chao Sun and Chiara Garibotto and Tran, {Duong Nguyen Ngoc} and Fabio Lavagetto and Halar Haleem and Hakki Motorcu and Ates, {Hasan F.} and Nguyen, {Huy Hung} and Jeon, {Hyung Joon} and Igor Bisio and Jeon, {Jae Wook} and Jiahao Li and Pham, {Long Hoang} and Moongu Jeon and Qianyu Feng and Shengwen Li and Tran, {Tai Huu Phuong} and Xiao Pan and Song, {Young Min} and Yuehan Yao and Yunhao Du and Zhenyu Xu and Zhipeng Luo",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 ; Conference date: 11-10-2021 Through 17-10-2021",

year = "2021",

doi = "10.1109/ICCVW54120.2021.00318",

language = "英语",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2839--2846",

booktitle = "Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021",

}

Chen, G, Wang, W, He, Z, Wang, L, Yuan, Y, Zhang, D, Zhang, J, Zhu, P, Van Gool, L, Han, J, Hoi, S, Hu, Q, Liu, M, Sciarrone, A, Sun, C, Garibotto, C, Tran, DNN, Lavagetto, F, Haleem, H, Motorcu, H, Ates, HF, Nguyen, HH, Jeon, HJ, Bisio, I, Jeon, JW, Li, J, Pham, LH, Jeon, M, Feng, Q, Li, S, Tran, THP, Pan, X, Song, YM, Yao, Y, Du, Y, Xu, Z & Luo, Z 2021, VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results. in Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. Proceedings of the IEEE International Conference on Computer Vision, vol. 2021-October, Institute of Electrical and Electronics Engineers Inc., pp. 2839-2846, 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Virtual, Online, Canada, 11/10/21. https://doi.org/10.1109/ICCVW54120.2021.00318

VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results. / Chen, Guanlin; Wang, Wenguan; He, Zhijian et al.
Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 2839-2846 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2021-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - VisDrone-MOT2021

T2 - 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021

AU - Chen, Guanlin

AU - Wang, Wenguan

AU - He, Zhijian

AU - Wang, Lujia

AU - Yuan, Yixuan

AU - Zhang, Dingwen

AU - Zhang, Jinglin

AU - Zhu, Pengfei

AU - Van Gool, Luc

AU - Han, Junwei

AU - Hoi, Steven

AU - Hu, Qinghua

AU - Liu, Ming

AU - Sciarrone, Andrea

AU - Sun, Chao

AU - Garibotto, Chiara

AU - Tran, Duong Nguyen Ngoc

AU - Lavagetto, Fabio

AU - Haleem, Halar

AU - Motorcu, Hakki

AU - Ates, Hasan F.

AU - Nguyen, Huy Hung

AU - Jeon, Hyung Joon

AU - Bisio, Igor

AU - Jeon, Jae Wook

AU - Li, Jiahao

AU - Pham, Long Hoang

AU - Jeon, Moongu

AU - Feng, Qianyu

AU - Li, Shengwen

AU - Tran, Tai Huu Phuong

AU - Pan, Xiao

AU - Song, Young Min

AU - Yao, Yuehan

AU - Du, Yunhao

AU - Xu, Zhenyu

AU - Luo, Zhipeng

PY - 2021

Y1 - 2021

N2 - Vision Meets Drone: Multiple Object Tracking (VisDrone-MOT2021) challenge - the forth annual activity organized by the VisDrone team - focuses on benchmarking UAV MOT algorithms in realistic challenging environments. It is held in conjunction with ICCV 2021. VisDrone-MOT2021 contains 96 video sequences in total, including 56 sequences (~24K frames) for training, 7 sequences (~3K frames) for validation and 33 sequences (~13K frames) for testing. Bounding-box annotations for novel object categories are provided every frame and temporally consistent instance IDs are also given. Additionally, occlusion ratio and truncation ratio are provided as extra useful annotations. The results of eight state-of-the-art MOT algorithms are reported and discussed. We hope that our VisDrone-MOT2021 challenge will facilitate future research and applications in the field of UAV vision. The website of our challenge can be found at http://www.aiskyeye.com/.

AB - Vision Meets Drone: Multiple Object Tracking (VisDrone-MOT2021) challenge - the forth annual activity organized by the VisDrone team - focuses on benchmarking UAV MOT algorithms in realistic challenging environments. It is held in conjunction with ICCV 2021. VisDrone-MOT2021 contains 96 video sequences in total, including 56 sequences (~24K frames) for training, 7 sequences (~3K frames) for validation and 33 sequences (~13K frames) for testing. Bounding-box annotations for novel object categories are provided every frame and temporally consistent instance IDs are also given. Additionally, occlusion ratio and truncation ratio are provided as extra useful annotations. The results of eight state-of-the-art MOT algorithms are reported and discussed. We hope that our VisDrone-MOT2021 challenge will facilitate future research and applications in the field of UAV vision. The website of our challenge can be found at http://www.aiskyeye.com/.

KW - Benchmark

KW - Challenge

KW - Drone

KW - Multi-object tracking

KW - VisDrone

UR - http://www.scopus.com/inward/record.url?scp=85122776407&partnerID=8YFLogxK

U2 - 10.1109/ICCVW54120.2021.00318

DO - 10.1109/ICCVW54120.2021.00318

M3 - 会议稿件

AN - SCOPUS:85122776407

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2839

EP - 2846

BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 11 October 2021 through 17 October 2021

ER -

Chen G, Wang W, He Z, Wang L, Yuan Y, Zhang D et al. VisDrone-MOT2021: The Vision Meets Drone Multiple Object Tracking Challenge Results. In Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 2839-2846. (Proceedings of the IEEE International Conference on Computer Vision). doi: 10.1109/ICCVW54120.2021.00318

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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this