ABSTRACT
Remote sensing data generated by satellites have important research and application values. However, traditional detection models have poor adaptability and generalization ability. In order to solve the low accuracy problem of the existing algorithm for small object detection of remote sensing, a small object detection algorithm MARNet (multi-angle rotation network) for remote sensing images of multi-angle rotation was proposed in this study, which used ResNet101 (residual network) as the baseline network. Global attention feature pyramid networks (GA_FPN) structure was designed based on the features of the pyramid network to improve the small object detection performance in remote sensing. Then MergeNet (Merge Network) was designed to better obtain the semantic relationship between features, and the attention mechanism was introduced to enhance the feature information of the target object. Datasets of DOTA (a large-scale dataset for object detection in aerial images) and NWPU VHR-10 (northwestern polytechnical university, very-high-resolution) are used to verify the algorithm.
Notes on contribution
Lianyu Cao is a PhD Candidate in the School of Computer and Communication Engineering, University of Science and Technology Beijing, China. He received his MS degree in engineering from TSINGHUA University. His research interests include computer vision and deep learning.
Xiaolu Zhang is a PhD Candidate in the School of Computer and Communication Engineering, University of Science and Technology Beijing, China. Her current research interests include deep learning, computer vision, and remote-sensing information processing.
Zhaoshun Wang is a professor in the School of Computer and Communication Engineering, University of Science and Technology Beijing, China. His main research interests include computer software, information security, and deep learning.
Guangyu Ding received his MS degree in engineering from Guangxi University in 2019. He is currently a deep learning algorithm engineer in HyperAI Tech. (Beijing) Co., Ltd., and he is engaged in deep learning, image processing, and research on AUTOML.
Disclosure statement
No potential conflict of interest was reported by the authors.