空天预警研究学报2023，Vol.37Issue(4)：285-289,5.DOI:10.3969/j.issn.2097-180X.2023.04.010
基于显著性CNN的SAR图像靠岸舰船检测方法
A saliency-based CNN method for inshore ship detection in SAR images
张天文 1张晓玲 1胥小我 1邵子康 1曾天娇2
作者信息
- 1. 电子科技大学信息与通信工程学院,成都 611731
- 2. 电子科技大学航空航天学院,成都 611731
- 折叠
摘要
Abstract
In order to improve the accuracy of convolutional neural network(CNN)for detecting inshore ships in SAR images,this paper proposes a saliency-based CNN method.In this method,the visual salience mech-anism is used to preprocess SAR images,then the obtained scene attention weight(i.e.,salience graph)is fused in-to the original SAR images,and finally the SAR images with scene attention weight is input into the CNN net-work.Experiments on public SAR ship detection datasets show that,compared with the classical two-stage detec-tor Faster R-CNN method,the saliency CNN method can suppress the shore background interference,and effec-tively improve the detection accuracy of SAR docked ships.关键词
合成孔径雷达/舰船检测/卷积神经网络/靠岸舰船Key words
SAR/ship detection/CNN/inshore ship分类
信息技术与安全科学引用本文复制引用
张天文,张晓玲,胥小我,邵子康,曾天娇..基于显著性CNN的SAR图像靠岸舰船检测方法[J].空天预警研究学报,2023,37(4):285-289,5.
