ICPR2018 Contest on Object Detection in Aerial Images (ODAI-18)
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
ICPR2018 Contest on Object Detection in Aerial Images (ODAI-18). / Ding, Jian; Zhu, Zhen; Xia, Gui Song; Bai, Xiang; Belongie, Serge; Luo, Jiebo; Datcu, Mihai; Pelillo, Marcello; Zhang, Liangpei.
2018 24th International Conference on Pattern Recognition (ICPR). IEEE, 2018. s. 1-6.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - ICPR2018 Contest on Object Detection in Aerial Images (ODAI-18)
AU - Ding, Jian
AU - Zhu, Zhen
AU - Xia, Gui Song
AU - Bai, Xiang
AU - Belongie, Serge
AU - Luo, Jiebo
AU - Datcu, Mihai
AU - Pelillo, Marcello
AU - Zhang, Liangpei
N1 - Funding Information: This challenge is supported by NSFC projects under the contracts No.61771350 and No.41501462. Dr. Xiang Bai is supported by the National Program for Support of Top-notch Young Professionals. We thank Linyan Cui, Pei Xu for the development of the evaluation server. We thank Pu Jin, Xinyi Tong, Xuan Hu, Zhipeng Dong, Liang Wu, Jun Tang, Duoyou Zhou, Tengteng Huang, and all the others for their efforts in annotating the data. Publisher Copyright: © 2018 IEEE.
PY - 2018
Y1 - 2018
N2 - Object detection in aerial images plays a significant role in intelligent interpretation of aerial images. Hence many effective methods, especially the new-generation data-driven methods, have been developed for this task. Here, we hold the ODAI, a new contest that focused on object detection in aerial images, based on a new large-scale aerial image dataset called DOTA [1]. This contest contains over 3000 large-size images (4k\times 4k pixels), which cover 211,581 instances divided into 15 categories. Each instance is labeled by an arbitrary (8 d.o.f.) quadrilateral. Besides, we propose two tasks for this contest, named object detection with the horizontal bounding box (OD-HBB) and object detection with the oriented bounding box (OD-OBB). The contest was opened on February 7, 2018, and ended on April 30, 2018. A website is open to the public, which provides links to download data and evaluation server. We have totally received 60 registrations. There are 8 teams that have successfully submitted results on the OD-HBB task with the top mAP as 0.719, and 9 teams that have successfully submitted results on the OD-OBB task with the top mAP as 0.705. Through the contest, we hope to draw extensive attention from a wide range of communities and call for more future research and efforts for the task of object detection in aerial images.
AB - Object detection in aerial images plays a significant role in intelligent interpretation of aerial images. Hence many effective methods, especially the new-generation data-driven methods, have been developed for this task. Here, we hold the ODAI, a new contest that focused on object detection in aerial images, based on a new large-scale aerial image dataset called DOTA [1]. This contest contains over 3000 large-size images (4k\times 4k pixels), which cover 211,581 instances divided into 15 categories. Each instance is labeled by an arbitrary (8 d.o.f.) quadrilateral. Besides, we propose two tasks for this contest, named object detection with the horizontal bounding box (OD-HBB) and object detection with the oriented bounding box (OD-OBB). The contest was opened on February 7, 2018, and ended on April 30, 2018. A website is open to the public, which provides links to download data and evaluation server. We have totally received 60 registrations. There are 8 teams that have successfully submitted results on the OD-HBB task with the top mAP as 0.719, and 9 teams that have successfully submitted results on the OD-OBB task with the top mAP as 0.705. Through the contest, we hope to draw extensive attention from a wide range of communities and call for more future research and efforts for the task of object detection in aerial images.
UR - http://www.scopus.com/inward/record.url?scp=85059772933&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2018.8546163
DO - 10.1109/ICPR.2018.8546163
M3 - Article in proceedings
AN - SCOPUS:85059772933
SP - 1
EP - 6
BT - 2018 24th International Conference on Pattern Recognition (ICPR)
PB - IEEE
T2 - 24th International Conference on Pattern Recognition, ICPR 2018
Y2 - 20 August 2018 through 24 August 2018
ER -
ID: 306464846