TY - GEN

T1 - DOTA

T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018

AU - Xia, Gui Song

AU - Bai, Xiang

AU - Ding, Jian

AU - Zhu, Zhen

AU - Belongie, Serge

AU - Luo, Jiebo

AU - Datcu, Mihai

AU - Pelillo, Marcello

AU - Zhang, Liangpei

N1 - Funding Information: This research 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 Topnotch Young Professionals. We thank Fan Hu, Pu Jin, Xinyi Tong, Xuan Hu, Zhipeng Dong, Liang Wu, Jun Tang, Linyan Cui, Duoyou Zhou, Tengteng Huang, and all the others who involved in the annotations of DOTA. Publisher Copyright: © 2018 IEEE.

PY - 2018/12/14

Y1 - 2018/12/14

N2 - Object detection is an important and challenging problem in computer vision. Although the past decade has witnessed major advances in object detection in natural scenes, such successes have been slow to aerial imagery, not only because of the huge variation in the scale, orientation and shape of the object instances on the earth's surface, but also due to the scarcity of well-annotated datasets of objects in aerial scenes. To advance object detection research in Earth Vision, also known as Earth Observation and Remote Sensing, we introduce a large-scale Dataset for Object deTection in Aerial images (DOTA). To this end, we collect 2806 aerial images from different sensors and platforms. Each image is of the size about 4000 Ã - 4000 pixels and contains objects exhibiting a wide variety of scales, orientations, and shapes. These DOTA images are then annotated by experts in aerial image interpretation using 15 common object categories. The fully annotated DOTA images contains 188, 282 instances, each of which is labeled by an arbitrary (8 d.o.f.) quadrilateral. To build a baseline for object detection in Earth Vision, we evaluate state-of-the-art object detection algorithms on DOTA. Experiments demonstrate that DOTA well represents real Earth Vision applications and are quite challenging.

AB - Object detection is an important and challenging problem in computer vision. Although the past decade has witnessed major advances in object detection in natural scenes, such successes have been slow to aerial imagery, not only because of the huge variation in the scale, orientation and shape of the object instances on the earth's surface, but also due to the scarcity of well-annotated datasets of objects in aerial scenes. To advance object detection research in Earth Vision, also known as Earth Observation and Remote Sensing, we introduce a large-scale Dataset for Object deTection in Aerial images (DOTA). To this end, we collect 2806 aerial images from different sensors and platforms. Each image is of the size about 4000 Ã - 4000 pixels and contains objects exhibiting a wide variety of scales, orientations, and shapes. These DOTA images are then annotated by experts in aerial image interpretation using 15 common object categories. The fully annotated DOTA images contains 188, 282 instances, each of which is labeled by an arbitrary (8 d.o.f.) quadrilateral. To build a baseline for object detection in Earth Vision, we evaluate state-of-the-art object detection algorithms on DOTA. Experiments demonstrate that DOTA well represents real Earth Vision applications and are quite challenging.

UR - http://www.scopus.com/inward/record.url?scp=85059781215&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2018.00418

DO - 10.1109/CVPR.2018.00418

M3 - Article in proceedings

AN - SCOPUS:85059781215

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 3974

EP - 3983

BT - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

PB - IEEE

Y2 - 18 June 2018 through 22 June 2018

ER -