TY - JOUR

T1 - Object Detection in Aerial Images

T2 - A Large-Scale Benchmark and Challenges

AU - Ding, Jian

AU - Xue, Nan

AU - Xia, Gui Song

AU - Bai, Xiang

AU - Yang, Wen

AU - Yang, Michael

AU - Belongie, Serge

AU - Luo, Jiebo

AU - Datcu, Mihai

AU - Pelillo, Marcello

AU - Zhang, Liangpei

N1 - Publisher Copyright: IEEE

PY - 2021

Y1 - 2021

N2 - In the past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.

AB - In the past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.

KW - aerial images

KW - benchmark dataset

KW - Codes

KW - Earth

KW - Libraries

KW - Object detection

KW - oriented object detection

KW - remote sensing

KW - Software

KW - Software algorithms

KW - Task analysis

UR - http://www.scopus.com/inward/record.url?scp=85119589943&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2021.3117983

DO - 10.1109/TPAMI.2021.3117983

M3 - Journal article

C2 - 34613910

AN - SCOPUS:85119589943

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

ER -