AUTHOR=Gao Shurun , Liu Chang , Zhang Haimiao , Zhou Zhehai , Qiu Jun 

TITLE=Multiscale attention-based detection of tiny targets in aerial beach images

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2022.1073615

DOI=10.3389/fmars.2022.1073615

ISSN=2296-7745

ABSTRACT=We proposed the feature pyramid network model based on multiscale attention to address the problem of tiny target detection in aerial beach images with large field-of-view, which forms the basis for the tiny target recognition and counting. The accurate detection of tiny targets in aerial beach images is affected by three difficulties: perspective multiscale, tiny target pixel ratios, and complex backgrounds. To improve the ability of the tiny targets' feature extraction, the proposed model focuses on different scales of the images to the target regions based on the multiscale attention enhancement module. To improve the effectiveness of tiny targets' feature fusion, the pyramid structure is guided by the feature fusion module in order to give further semantic information to the low-level feature maps and prevent the tiny targets from being overwhelmed by the information at the high-level. The accuracy of the proposed model on the TinyPerson dataset is 59.82%, which effectively improved the detection accuracy compared to the state-of-the-art model.