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

By Jian Ding, Nan Xue, Guisong Xia, Xiang Bai, Wen Yang, Mingkun Yang, Serge J. Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo and 1 more. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021

655 citations recorded by the source corpus.

In he 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2e7fc1774dacd80496edbe6957ddea9ada98dad1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ji Qi
2. Feng Xu
3. Ke Yan
4. Zhiyuan Yan
5. Peijin Wang
6. Haifeng Li
7. Ruiping Wang
8. Tong Zhang

In Computer Vision and Pattern Recognition

1. Gong Cheng
2. Junwei Han
3. Xiwen Yao
4. Chao Tao
5. Kun Fu
6. Xian Sun
7. Haifeng Li
8. Ruiping Wang

Citations in the corpus

• Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “In the past decades, various research institutions have launched plenty of high-quality datasets [6], [30], [31], [32], and these publicly available benchmarks provide impartial platforms for validating the detection methods and significantly boost the development of related fields.”
• FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery (2021, methodology): “The implement of these methods is built based on the code library [3, 14, 60].”
• EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain (2024, methodology): “When integrating nature pretraining and RS fine-tuning, the Top-1 accuracy increases by 7.37%.”
• Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark (2022, neutral): “0 (Ding et al., 2021).”
• Poly Kernel Inception Network for Remote Sensing Detection (2024, background): “Object detection in remote sensing images (RSIs) has gained substantial attention in recent years [11, 56, 64].”
• Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs (2022, methodology): “DOTA [8–10], without changing any hyperparameters.”
• Self-Supervised Remote Sensing Feature Learning: Learning Paradigms, Challenges, and Future Works (2022, background): “0 [9], [252], a large-scale object detection dataset containing 188 282 objects of 15 cat-”