Cascaded Feature Fusion Pyramid Network for Ship Detection in Dualpolarization SAR Images

Synthetic aperture radar (SAR) has been widely applied in maritime target detection. However, most existing SAR ship detection algorithms based on convolutional neural network (CNN) only use single polarization SAR images for detection, neglecting to further improve the detection performance by util...

Full description

Saved in:
Bibliographic Details
Published inIGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium pp. 9931 - 9934
Main Authors Tang, Xue, Shang, Yuanzhe, Xu, Honglin, Pei, Jifang, Zhang, Yin, Huo, Weibo, Huang, Yulin
Format Conference Proceeding
LanguageEnglish
Published IEEE 07.07.2024
Subjects
convolutional neural network
dual polarization
Feature extraction
feature fusion
Geoscience and remote sensing
Interference
Neural networks
Noise
Radar polarimetry
ship detection
synthetic aperture radar (SAR)
YOLO
Online AccessGet full text

Cover

More Information
Summary:Synthetic aperture radar (SAR) has been widely applied in maritime target detection. However, most existing SAR ship detection algorithms based on convolutional neural network (CNN) only use single polarization SAR images for detection, neglecting to further improve the detection performance by utilizing the rich polarization information of the SAR images. To deal with this issue, this paper proposes a Cascaded Feature Fusion Pyramid Network (CFFPN) for ship detection in dual-polarization SAR images. The CFFPN builds a cascaded feature fusion module (CFFM) to fuse the enriched polarization information in SAR images. Extensive evaluations conducted on the the dual-polarization SAR ship detection dataset showcase the remarkable effectiveness of CFFPN, achieving an average precision (AP) of 93.4%. This outperforms the other five competitive methods. Notably, CFFPN exhibits a notable improvement of 1.3% in AP compared to the second-best method.
ISSN:2153-7003
DOI:10.1109/IGARSS53475.2024.10640748