VisDrone-CC2021: The Vision Meets Drone Crowd Counting Challenge Results

Zhihao Liu; Zhijian He; Lujia Wang; Wenguan Wang; Yixuan Yuan; Dingwen Zhang; Jinglin Zhang; Pengfei Zhu; Luc Van Gool; Junwei Han; Steven Hoi; Qinghua Hu; Ming Liu; Junwen Pan; Baoqun Yin; Binyu Zhang; Chengxin Liu; Ding Ding; Dingkang Liang; Guanchen Ding; Hao Lu; Hui Lin; Jingyuan Chen; Jiong Li; Liang Liu; Lin Zhou; Min Shi; Qianqian Yang; Qing He; Sifan Peng; Wei Xu; Wenwei Han; Xiang Bai; Xiwu Chen; Yabin Wang; Yinfeng Xia; Yiran Tao; Zhenzhong Chen; Zhiguo Cao

doi:10.1109/ICCVW54120.2021.00317

VisDrone-CC2021: The Vision Meets Drone Crowd Counting Challenge Results

Zhihao Liu, Zhijian He, Lujia Wang, Wenguan Wang, Yixuan Yuan, Dingwen Zhang, Jinglin Zhang, Pengfei Zhu, Luc Van Gool, Junwei Han, Steven Hoi, Qinghua Hu, Ming Liu, Junwen Pan, Baoqun Yin, Binyu Zhang, Chengxin Liu, Ding Ding, Dingkang Liang, Guanchen DingHao Lu, Hui Lin, Jingyuan Chen, Jiong Li, Liang Liu, Lin Zhou, Min Shi, Qianqian Yang, Qing He, Sifan Peng, Wei Xu, Wenwei Han, Xiang Bai, Xiwu Chen, Yabin Wang, Yinfeng Xia, Yiran Tao, Zhenzhong Chen, Zhiguo Cao

School of Automation

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

25 Scopus citations

Abstract

Crowding counting research evolves quickly by the lever-age of development in deep learning. Many researchers put their efforts into crowd counting tasks and have achieved many significant improvements. However, current datasets still barely satisfy this evolution and high quality evaluation data is urgent. Motivated by high quality and quantity study in crowding counting, we collect a drone-captured dataset formed by 5, 468 images(images in RGB and thermal appear in pairs and 2, 734 respectively). There are 1, 807 pairs of images for training, and 927 pairs for testing. We manually annotate persons with points in each frame. Based on this dataset, we organized the Vision Meets Drone Crowd Counting Challenge(Visdrone-CC2021) in conjunction with the International Conference on Computer Vision (ICCV 2021). Our challenge attracts many researchers to join, which pave the road of speed up the milestone in crowding counting. To summarize the competition, we select the most remarkable algorithms from participants' sub-missions and provide a detailed analysis of the evaluation results. More information can be found at the website: 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	2830-2838
Number of pages	9
ISBN (Electronic)	9781665401913
DOIs	https://doi.org/10.1109/ICCVW54120.2021.00317
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

Access to Document

10.1109/ICCVW54120.2021.00317

Cite this

Liu, Z., He, Z., Wang, L., Wang, W., Yuan, Y., Zhang, D., Zhang, J., Zhu, P., Gool, L. V., Han, J., Hoi, S., Hu, Q., Liu, M., Pan, J., Yin, B., Zhang, B., Liu, C., Ding, D., Liang, D., ... Cao, Z. (2021). VisDrone-CC2021: The Vision Meets Drone Crowd Counting Challenge Results. In Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 (pp. 2830-2838). (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2021-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW54120.2021.00317

@inproceedings{7f421c70801a46a98773a984a730043c,

title = "VisDrone-CC2021: The Vision Meets Drone Crowd Counting Challenge Results",

abstract = "Crowding counting research evolves quickly by the lever-age of development in deep learning. Many researchers put their efforts into crowd counting tasks and have achieved many significant improvements. However, current datasets still barely satisfy this evolution and high quality evaluation data is urgent. Motivated by high quality and quantity study in crowding counting, we collect a drone-captured dataset formed by 5, 468 images(images in RGB and thermal appear in pairs and 2, 734 respectively). There are 1, 807 pairs of images for training, and 927 pairs for testing. We manually annotate persons with points in each frame. Based on this dataset, we organized the Vision Meets Drone Crowd Counting Challenge(Visdrone-CC2021) in conjunction with the International Conference on Computer Vision (ICCV 2021). Our challenge attracts many researchers to join, which pave the road of speed up the milestone in crowding counting. To summarize the competition, we select the most remarkable algorithms from participants' sub-missions and provide a detailed analysis of the evaluation results. More information can be found at the website: http://www.aiskyeye.com/.",

author = "Zhihao Liu and Zhijian He and Lujia Wang and Wenguan Wang and Yixuan Yuan and Dingwen Zhang and Jinglin Zhang and Pengfei Zhu and Gool, {Luc Van} and Junwei Han and Steven Hoi and Qinghua Hu and Ming Liu and Junwen Pan and Baoqun Yin and Binyu Zhang and Chengxin Liu and Ding Ding and Dingkang Liang and Guanchen Ding and Hao Lu and Hui Lin and Jingyuan Chen and Jiong Li and Liang Liu and Lin Zhou and Min Shi and Qianqian Yang and Qing He and Sifan Peng and Wei Xu and Wenwei Han and Xiang Bai and Xiwu Chen and Yabin Wang and Yinfeng Xia and Yiran Tao and Zhenzhong Chen and Zhiguo Cao",

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/ICCVW54120.2021.00317",

language = "英语",

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

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

pages = "2830--2838",

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

}

Liu, Z, He, Z, Wang, L, Wang, W, Yuan, Y, Zhang, D, Zhang, J, Zhu, P, Gool, LV, Han, J, Hoi, S, Hu, Q, Liu, M, Pan, J, Yin, B, Zhang, B, Liu, C, Ding, D, Liang, D, Ding, G, Lu, H, Lin, H, Chen, J, Li, J, Liu, L, Zhou, L, Shi, M, Yang, Q, He, Q, Peng, S, Xu, W, Han, W, Bai, X, Chen, X, Wang, Y, Xia, Y, Tao, Y, Chen, Z & Cao, Z 2021, VisDrone-CC2021: The Vision Meets Drone Crowd Counting 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. 2830-2838, 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Virtual, Online, Canada, 11/10/21. https://doi.org/10.1109/ICCVW54120.2021.00317

VisDrone-CC2021: The Vision Meets Drone Crowd Counting Challenge Results. / Liu, Zhihao; He, Zhijian; Wang, Lujia et al.
Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 2830-2838 (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-CC2021

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

AU - Liu, Zhihao

AU - He, Zhijian

AU - Wang, Lujia

AU - Wang, Wenguan

AU - Yuan, Yixuan

AU - Zhang, Dingwen

AU - Zhang, Jinglin

AU - Zhu, Pengfei

AU - Gool, Luc Van

AU - Han, Junwei

AU - Hoi, Steven

AU - Hu, Qinghua

AU - Liu, Ming

AU - Pan, Junwen

AU - Yin, Baoqun

AU - Zhang, Binyu

AU - Liu, Chengxin

AU - Ding, Ding

AU - Liang, Dingkang

AU - Ding, Guanchen

AU - Lu, Hao

AU - Lin, Hui

AU - Chen, Jingyuan

AU - Li, Jiong

AU - Liu, Liang

AU - Zhou, Lin

AU - Shi, Min

AU - Yang, Qianqian

AU - He, Qing

AU - Peng, Sifan

AU - Xu, Wei

AU - Han, Wenwei

AU - Bai, Xiang

AU - Chen, Xiwu

AU - Wang, Yabin

AU - Xia, Yinfeng

AU - Tao, Yiran

AU - Chen, Zhenzhong

AU - Cao, Zhiguo

PY - 2021

Y1 - 2021

N2 - Crowding counting research evolves quickly by the lever-age of development in deep learning. Many researchers put their efforts into crowd counting tasks and have achieved many significant improvements. However, current datasets still barely satisfy this evolution and high quality evaluation data is urgent. Motivated by high quality and quantity study in crowding counting, we collect a drone-captured dataset formed by 5, 468 images(images in RGB and thermal appear in pairs and 2, 734 respectively). There are 1, 807 pairs of images for training, and 927 pairs for testing. We manually annotate persons with points in each frame. Based on this dataset, we organized the Vision Meets Drone Crowd Counting Challenge(Visdrone-CC2021) in conjunction with the International Conference on Computer Vision (ICCV 2021). Our challenge attracts many researchers to join, which pave the road of speed up the milestone in crowding counting. To summarize the competition, we select the most remarkable algorithms from participants' sub-missions and provide a detailed analysis of the evaluation results. More information can be found at the website: http://www.aiskyeye.com/.

AB - Crowding counting research evolves quickly by the lever-age of development in deep learning. Many researchers put their efforts into crowd counting tasks and have achieved many significant improvements. However, current datasets still barely satisfy this evolution and high quality evaluation data is urgent. Motivated by high quality and quantity study in crowding counting, we collect a drone-captured dataset formed by 5, 468 images(images in RGB and thermal appear in pairs and 2, 734 respectively). There are 1, 807 pairs of images for training, and 927 pairs for testing. We manually annotate persons with points in each frame. Based on this dataset, we organized the Vision Meets Drone Crowd Counting Challenge(Visdrone-CC2021) in conjunction with the International Conference on Computer Vision (ICCV 2021). Our challenge attracts many researchers to join, which pave the road of speed up the milestone in crowding counting. To summarize the competition, we select the most remarkable algorithms from participants' sub-missions and provide a detailed analysis of the evaluation results. More information can be found at the website: http://www.aiskyeye.com/.

UR - http://www.scopus.com/inward/record.url?scp=85123045489&partnerID=8YFLogxK

U2 - 10.1109/ICCVW54120.2021.00317

DO - 10.1109/ICCVW54120.2021.00317

M3 - 会议稿件

AN - SCOPUS:85123045489

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2830

EP - 2838

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 -

Liu Z, He Z, Wang L, Wang W, Yuan Y, Zhang D et al. VisDrone-CC2021: The Vision Meets Drone Crowd Counting Challenge Results. In Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 2830-2838. (Proceedings of the IEEE International Conference on Computer Vision). doi: 10.1109/ICCVW54120.2021.00317

VisDrone-CC2021: The Vision Meets Drone Crowd Counting Challenge Results

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this