Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges

TL;DR

This paper introduces a large-scale aerial image dataset called DOTA, along with comprehensive benchmarks and tools, to advance object detection research in aerial imagery characterized by high variability in object scale and orientation.

Contribution

The paper presents the DOTA dataset with extensive annotations, establishes multiple baseline algorithms, and provides tools and challenges to foster progress in aerial image object detection.

Findings

DOTA contains 1,793,658 object instances across 18 categories.

Baseline algorithms achieve varying accuracy and speed on DOTA.

Over 1300 teams participated in challenges using DOTA.

Abstract

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.