VisDrone-SOT2018: the vision meets drone single-object tracking challenge results

Longyin Wen; Pengfei Zhu; Dawei Du; Xiao Bian; Haibin Ling; Qinghua Hu; Chenfeng Liu; Hao Cheng; Xiaoyu Liu; Wenya Ma; Qinqin Nie; Haotian Wu; Lianjie Wang; Asanka G. Perera; Baochang Zhang; Byeongho Heo; Chunlei Liu; Dongdong Li; Emmanouil Michail; Hanlin Chen; Hao Liu; Haojie Li; Ioannis Kompatsiaris; Jian Cheng; Jiaqing Fan; Jie Zhang; Jin Young Choi; Jing Li; Jinyu Yang; Jongwon Choi; Juanping Zhao; Jungong Han; Kaihua Zhang; Kaiwen Duan; Ke Song; Konstantinos Avgerinakis; Kyuewang Lee; Lu Ding; Martin Lauer; Panagiotis Giannakeris; Peizhen Zhang; Qiang Wang; Qianqian Xu; Qingming Huang; Qingshan Liu; Robert Laganière; Ruixin Zhang; Sangdoo Yun; Shengyin Zhu; Sihang Wu; Stefanos Vrochidis; Wei Tian; Wei Zhang; Weidong Chen; Weiming Hu; Wenhao Wang; Wenhua Zhang; Wenrui Ding; Xiaohao He; Xiaotong Li; Xin Zhang; Xinbin Luo; Xixi Hu; Yang Meng; Yangliu Kuai; Yanyun Zhao; Yaxuan Li; Yifan Yang; Yifan Zhang; Yong Wang; Yuankai Qi; Zhipeng Deng; Zhiqun He

doi:10.1007/978-3-030-11021-5_28

VisDrone-SOT2018: the vision meets drone single-object tracking challenge results

Longyin Wen, Pengfei Zhu^*, Dawei Du, Xiao Bian, Haibin Ling, Qinghua Hu, Chenfeng Liu, Hao Cheng, Xiaoyu Liu, Wenya Ma, Qinqin Nie, Haotian Wu, Lianjie Wang, Asanka G. Perera, Baochang Zhang, Byeongho Heo, Chunlei Liu, Dongdong Li, Emmanouil Michail, Hanlin ChenHao Liu, Haojie Li, Ioannis Kompatsiaris, Jian Cheng, Jiaqing Fan, Jie Zhang, Jin Young Choi, Jing Li, Jinyu Yang, Jongwon Choi, Juanping Zhao, Jungong Han, Kaihua Zhang, Kaiwen Duan, Ke Song, Konstantinos Avgerinakis, Kyuewang Lee, Lu Ding, Martin Lauer, Panagiotis Giannakeris, Peizhen Zhang, Qiang Wang, Qianqian Xu, Qingming Huang, Qingshan Liu, Robert Laganière, Ruixin Zhang, Sangdoo Yun, Shengyin Zhu, Sihang Wu, Stefanos Vrochidis, Wei Tian, Wei Zhang, Weidong Chen, Weiming Hu, Wenhao Wang, Wenhua Zhang, Wenrui Ding, Xiaohao He, Xiaotong Li, Xin Zhang, Xinbin Luo, Xixi Hu, Yang Meng, Yangliu Kuai, Yanyun Zhao, Yaxuan Li, Yifan Yang, Yifan Zhang, Yong Wang, Yuankai Qi, Zhipeng Deng, Zhiqun He

^*Corresponding author for this work

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

23 Citations (Scopus)

Abstract

Single-object tracking, also known as visual tracking, on the drone platform attracts much attention recently with various applications in computer vision, such as filming and surveillance. However, the lack of commonly accepted annotated datasets and standard evaluation platform prevent the developments of algorithms. To address this issue, the Vision Meets Drone Single-Object Tracking (VisDrone-SOT2018) Challenge workshop was organized in conjunction with the 15th European Conference on Computer Vision (ECCV 2018) to track and advance the technologies in such field. Specifically, we collect a dataset, including 132 video sequences divided into three non-overlapping sets, i.e., training (86 sequences with 69, 941 frames), validation (11 sequences with 7,046 frames), and testing (35 sequences with 29, 367 frames) sets. We provide fully annotated bounding boxes of the targets as well as several useful attributes, e.g., occlusion, background clutter, and camera motion. The tracking targets in these sequences include pedestrians, cars, buses, and animals. The dataset is extremely challenging due to various factors, such as occlusion, large scale, pose variation, and fast motion. We present the evaluation protocol of the VisDrone-SOT2018 challenge and the results of a comparison of 22 trackers on the benchmark dataset, which are publicly available on the challenge website: http://www.aiskyeye.com/. We hope this challenge largely boosts the research and development in single object tracking on drone platforms.

Original language	English
Title of host publication	Computer Vision – ECCV 2018 Workshops
Subtitle of host publication	Munich, Germany, September 8-14, 2018, proceedings, part V
Editors	Laura Leal-Taixé, Stefan Roth
Place of Publication	Cham
Publisher	Springer, Springer Nature
Pages	469-495
Number of pages	27
ISBN (Electronic)	9783030110215
ISBN (Print)	9783030110208
DOIs	https://doi.org/10.1007/978-3-030-11021-5_28
Publication status	Published - 2019
Externally published	Yes
Event	15th European Conference on Computer Vision, ECCV 2018 - Munich, Germany Duration: 8 Sept 2018 → 14 Sept 2018

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	11133
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	15th European Conference on Computer Vision, ECCV 2018
Country/Territory	Germany
City	Munich
Period	8/09/18 → 14/09/18

Keywords

Performance evaluation
Drone
Single-object tracking

Access to Document

10.1007/978-3-030-11021-5_28

Cite this

Wen, L., Zhu, P., Du, D., Bian, X., Ling, H., Hu, Q., Liu, C., Cheng, H., Liu, X., Ma, W., Nie, Q., Wu, H., Wang, L., Perera, A. G., Zhang, B., Heo, B., Liu, C., Li, D., Michail, E., ... He, Z. (2019). VisDrone-SOT2018: the vision meets drone single-object tracking challenge results. In L. Leal-Taixé, & S. Roth (Eds.), Computer Vision – ECCV 2018 Workshops: Munich, Germany, September 8-14, 2018, proceedings, part V (pp. 469-495). (Lecture Notes in Computer Science; Vol. 11133). Springer, Springer Nature. https://doi.org/10.1007/978-3-030-11021-5_28

@inproceedings{ecb0bc7b28164e6ba22c99e37f65732a,

title = "VisDrone-SOT2018: the vision meets drone single-object tracking challenge results",

abstract = "Single-object tracking, also known as visual tracking, on the drone platform attracts much attention recently with various applications in computer vision, such as filming and surveillance. However, the lack of commonly accepted annotated datasets and standard evaluation platform prevent the developments of algorithms. To address this issue, the Vision Meets Drone Single-Object Tracking (VisDrone-SOT2018) Challenge workshop was organized in conjunction with the 15th European Conference on Computer Vision (ECCV 2018) to track and advance the technologies in such field. Specifically, we collect a dataset, including 132 video sequences divided into three non-overlapping sets, i.e., training (86 sequences with 69, 941 frames), validation (11 sequences with 7,046 frames), and testing (35 sequences with 29, 367 frames) sets. We provide fully annotated bounding boxes of the targets as well as several useful attributes, e.g., occlusion, background clutter, and camera motion. The tracking targets in these sequences include pedestrians, cars, buses, and animals. The dataset is extremely challenging due to various factors, such as occlusion, large scale, pose variation, and fast motion. We present the evaluation protocol of the VisDrone-SOT2018 challenge and the results of a comparison of 22 trackers on the benchmark dataset, which are publicly available on the challenge website: http://www.aiskyeye.com/. We hope this challenge largely boosts the research and development in single object tracking on drone platforms.",

keywords = "Performance evaluation, Drone, Single-object tracking",

author = "Longyin Wen and Pengfei Zhu and Dawei Du and Xiao Bian and Haibin Ling and Qinghua Hu and Chenfeng Liu and Hao Cheng and Xiaoyu Liu and Wenya Ma and Qinqin Nie and Haotian Wu and Lianjie Wang and Perera, {Asanka G.} and Baochang Zhang and Byeongho Heo and Chunlei Liu and Dongdong Li and Emmanouil Michail and Hanlin Chen and Hao Liu and Haojie Li and Ioannis Kompatsiaris and Jian Cheng and Jiaqing Fan and Jie Zhang and Choi, {Jin Young} and Jing Li and Jinyu Yang and Jongwon Choi and Juanping Zhao and Jungong Han and Kaihua Zhang and Kaiwen Duan and Ke Song and Konstantinos Avgerinakis and Kyuewang Lee and Lu Ding and Martin Lauer and Panagiotis Giannakeris and Peizhen Zhang and Qiang Wang and Qianqian Xu and Qingming Huang and Qingshan Liu and Robert Lagani{\`e}re and Ruixin Zhang and Sangdoo Yun and Shengyin Zhu and Sihang Wu and Stefanos Vrochidis and Wei Tian and Wei Zhang and Weidong Chen and Weiming Hu and Wenhao Wang and Wenhua Zhang and Wenrui Ding and Xiaohao He and Xiaotong Li and Xin Zhang and Xinbin Luo and Xixi Hu and Yang Meng and Yangliu Kuai and Yanyun Zhao and Yaxuan Li and Yifan Yang and Yifan Zhang and Yong Wang and Yuankai Qi and Zhipeng Deng and Zhiqun He",

year = "2019",

doi = "10.1007/978-3-030-11021-5_28",

language = "English",

isbn = "9783030110208",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Springer Nature",

pages = "469--495",

editor = "Laura Leal-Taix{\'e} and Stefan Roth",

booktitle = "Computer Vision – ECCV 2018 Workshops",

address = "United States",

note = "15th European Conference on Computer Vision, ECCV 2018 ; Conference date: 08-09-2018 Through 14-09-2018",

}

Wen, L, Zhu, P, Du, D, Bian, X, Ling, H, Hu, Q, Liu, C, Cheng, H, Liu, X, Ma, W, Nie, Q, Wu, H, Wang, L, Perera, AG, Zhang, B, Heo, B, Liu, C, Li, D, Michail, E, Chen, H, Liu, H, Li, H, Kompatsiaris, I, Cheng, J, Fan, J, Zhang, J, Choi, JY, Li, J, Yang, J, Choi, J, Zhao, J, Han, J, Zhang, K, Duan, K, Song, K, Avgerinakis, K, Lee, K, Ding, L, Lauer, M, Giannakeris, P, Zhang, P, Wang, Q, Xu, Q, Huang, Q, Liu, Q, Laganière, R, Zhang, R, Yun, S, Zhu, S, Wu, S, Vrochidis, S, Tian, W, Zhang, W, Chen, W, Hu, W, Wang, W, Zhang, W, Ding, W, He, X, Li, X, Zhang, X, Luo, X, Hu, X, Meng, Y, Kuai, Y, Zhao, Y, Li, Y, Yang, Y, Zhang, Y, Wang, Y, Qi, Y, Deng, Z & He, Z 2019, VisDrone-SOT2018: the vision meets drone single-object tracking challenge results. in L Leal-Taixé & S Roth (eds), Computer Vision – ECCV 2018 Workshops: Munich, Germany, September 8-14, 2018, proceedings, part V. Lecture Notes in Computer Science, vol. 11133, Springer, Springer Nature, Cham, pp. 469-495, 15th European Conference on Computer Vision, ECCV 2018, Munich, Germany, 8/09/18. https://doi.org/10.1007/978-3-030-11021-5_28

VisDrone-SOT2018: the vision meets drone single-object tracking challenge results. / Wen, Longyin; Zhu, Pengfei; Du, Dawei et al.
Computer Vision – ECCV 2018 Workshops: Munich, Germany, September 8-14, 2018, proceedings, part V. ed. / Laura Leal-Taixé; Stefan Roth. Cham: Springer, Springer Nature, 2019. p. 469-495 (Lecture Notes in Computer Science; Vol. 11133).

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

TY - GEN

T1 - VisDrone-SOT2018

T2 - 15th European Conference on Computer Vision, ECCV 2018

AU - Wen, Longyin

AU - Zhu, Pengfei

AU - Du, Dawei

AU - Bian, Xiao

AU - Ling, Haibin

AU - Hu, Qinghua

AU - Liu, Chenfeng

AU - Cheng, Hao

AU - Liu, Xiaoyu

AU - Ma, Wenya

AU - Nie, Qinqin

AU - Wu, Haotian

AU - Wang, Lianjie

AU - Perera, Asanka G.

AU - Zhang, Baochang

AU - Heo, Byeongho

AU - Liu, Chunlei

AU - Li, Dongdong

AU - Michail, Emmanouil

AU - Chen, Hanlin

AU - Liu, Hao

AU - Li, Haojie

AU - Kompatsiaris, Ioannis

AU - Cheng, Jian

AU - Fan, Jiaqing

AU - Zhang, Jie

AU - Choi, Jin Young

AU - Li, Jing

AU - Yang, Jinyu

AU - Choi, Jongwon

AU - Zhao, Juanping

AU - Han, Jungong

AU - Zhang, Kaihua

AU - Duan, Kaiwen

AU - Song, Ke

AU - Avgerinakis, Konstantinos

AU - Lee, Kyuewang

AU - Ding, Lu

AU - Lauer, Martin

AU - Giannakeris, Panagiotis

AU - Zhang, Peizhen

AU - Wang, Qiang

AU - Xu, Qianqian

AU - Huang, Qingming

AU - Liu, Qingshan

AU - Laganière, Robert

AU - Zhang, Ruixin

AU - Yun, Sangdoo

AU - Zhu, Shengyin

AU - Wu, Sihang

AU - Vrochidis, Stefanos

AU - Tian, Wei

AU - Zhang, Wei

AU - Chen, Weidong

AU - Hu, Weiming

AU - Wang, Wenhao

AU - Zhang, Wenhua

AU - Ding, Wenrui

AU - He, Xiaohao

AU - Li, Xiaotong

AU - Zhang, Xin

AU - Luo, Xinbin

AU - Hu, Xixi

AU - Meng, Yang

AU - Kuai, Yangliu

AU - Zhao, Yanyun

AU - Li, Yaxuan

AU - Yang, Yifan

AU - Zhang, Yifan

AU - Wang, Yong

AU - Qi, Yuankai

AU - Deng, Zhipeng

AU - He, Zhiqun

PY - 2019

Y1 - 2019

N2 - Single-object tracking, also known as visual tracking, on the drone platform attracts much attention recently with various applications in computer vision, such as filming and surveillance. However, the lack of commonly accepted annotated datasets and standard evaluation platform prevent the developments of algorithms. To address this issue, the Vision Meets Drone Single-Object Tracking (VisDrone-SOT2018) Challenge workshop was organized in conjunction with the 15th European Conference on Computer Vision (ECCV 2018) to track and advance the technologies in such field. Specifically, we collect a dataset, including 132 video sequences divided into three non-overlapping sets, i.e., training (86 sequences with 69, 941 frames), validation (11 sequences with 7,046 frames), and testing (35 sequences with 29, 367 frames) sets. We provide fully annotated bounding boxes of the targets as well as several useful attributes, e.g., occlusion, background clutter, and camera motion. The tracking targets in these sequences include pedestrians, cars, buses, and animals. The dataset is extremely challenging due to various factors, such as occlusion, large scale, pose variation, and fast motion. We present the evaluation protocol of the VisDrone-SOT2018 challenge and the results of a comparison of 22 trackers on the benchmark dataset, which are publicly available on the challenge website: http://www.aiskyeye.com/. We hope this challenge largely boosts the research and development in single object tracking on drone platforms.

AB - Single-object tracking, also known as visual tracking, on the drone platform attracts much attention recently with various applications in computer vision, such as filming and surveillance. However, the lack of commonly accepted annotated datasets and standard evaluation platform prevent the developments of algorithms. To address this issue, the Vision Meets Drone Single-Object Tracking (VisDrone-SOT2018) Challenge workshop was organized in conjunction with the 15th European Conference on Computer Vision (ECCV 2018) to track and advance the technologies in such field. Specifically, we collect a dataset, including 132 video sequences divided into three non-overlapping sets, i.e., training (86 sequences with 69, 941 frames), validation (11 sequences with 7,046 frames), and testing (35 sequences with 29, 367 frames) sets. We provide fully annotated bounding boxes of the targets as well as several useful attributes, e.g., occlusion, background clutter, and camera motion. The tracking targets in these sequences include pedestrians, cars, buses, and animals. The dataset is extremely challenging due to various factors, such as occlusion, large scale, pose variation, and fast motion. We present the evaluation protocol of the VisDrone-SOT2018 challenge and the results of a comparison of 22 trackers on the benchmark dataset, which are publicly available on the challenge website: http://www.aiskyeye.com/. We hope this challenge largely boosts the research and development in single object tracking on drone platforms.

KW - Performance evaluation

KW - Drone

KW - Single-object tracking

UR - http://www.scopus.com/inward/record.url?scp=85061699928&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-11021-5_28

DO - 10.1007/978-3-030-11021-5_28

M3 - Conference proceeding contribution

AN - SCOPUS:85061699928

SN - 9783030110208

T3 - Lecture Notes in Computer Science

SP - 469

EP - 495

BT - Computer Vision – ECCV 2018 Workshops

A2 - Leal-Taixé, Laura

A2 - Roth, Stefan

PB - Springer, Springer Nature

CY - Cham

Y2 - 8 September 2018 through 14 September 2018

ER -

Wen L, Zhu P, Du D, Bian X, Ling H, Hu Q et al. VisDrone-SOT2018: the vision meets drone single-object tracking challenge results. In Leal-Taixé L, Roth S, editors, Computer Vision – ECCV 2018 Workshops: Munich, Germany, September 8-14, 2018, proceedings, part V. Cham: Springer, Springer Nature. 2019. p. 469-495. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-11021-5_28

VisDrone-SOT2018: the vision meets drone single-object tracking challenge results

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this