A Hybrid Features Based Detection Method for Inshore Ship Targets in SAR Imagery

作     者：Tong ZHENG Peng LEI Jun WANG Tong ZHENG;Peng LEI;Jun WANG

作者机构：School of Artificial IntelligenceBeijing Technology and Business UniversityBeijing 100031China School of Electronic and Information EngineeringBeihang UniversityBeijing 100083China 

出 版 物：《Journal of Geodesy and Geoinformation Science》 (测绘学报（英文版）)

年 卷 期：2023年第6卷第1期

页      面：95-107页

核心收录：

学科分类：11[军事学] 080904[工学-电磁场与微波技术] 0810[工学-信息与通信工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 081105[工学-导航、制导与控制] 081001[工学-通信与信息系统] 081002[工学-信号与信息处理] 0825[工学-航空宇航科学与技术] 1109[军事学-军事装备学] 0811[工学-控制科学与工程] 

基　　金：Aeronautical Science Foundation of China(No.2018ZC51022) 

主　　题：Convolutional Neural Network(CNN) Synthetic Aperture Radar(SAR) inshore ship detection hybrid features high-energy point number amplitude spectrum 

摘      要：Convolutional Neural Networks(CNNs)have recently attracted much attention in the ship detection from Synthetic Aperture Radar(SAR)***,compared with optical images,SAR ones are hard to ***,due to the high similarity between the man-made targets near shore and inshore ships,the classical methods are unable to achieve effective detection of inshore *** mitigate the influence of onshore ship-like objects,this paper proposes an inshore ship detection method in SAR images by using hybrid ***,the sea-land segmentation is applied in the pre-processing to exclude obvious land regions from SAR ***,a CNN model is designed to extract deep features for identifying potential ship targets in both inshore and offshore *** this basis,the high-energy point number of amplitude spectrum is further introduced as an important and delicate feature to suppress false alarms ***,to verify the effectiveness of the proposed method,numerical and comparative studies are carried out in experiments on Sentinel-1 SAR images.