Abstract

Aiming at the problem of missing detection caused by the densely arranged targets in remote sensing images, a target detection algorithm based on multi-dimension attention is proposed. The proposed algorithm uses the RetinaNet target detector as the main framework. Firstly, the backbone network is used to extract feature maps of different scales. Secondly, the Feature Pyramid Net (FPN) is used to realize the fusion of feature maps of different scales. Then, the feature map through the attention module is used to suppress the boundary noise and highlight the target features. Finally, the class and box subnets are used to classify and locate the target. The experimental results show that, compared with the RetinaNet algorithm, the mean Average Precision (mAP) of the improved algorithm on small-DOTA is improved by 5.55%.

Full Text

Published Version

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.