摘要
为了克服Radon变换用于合成孔径雷达(SAR)图像中的船舶尾迹检测的缺陷,提出了一种基于Radon变换和尾迹模型的尾迹检测算法,可以有效地检测出大幅SAR图像中的船舶尾迹。该算法利用结合梯度的归一化Radon变换增强了变换域中的峰谷值,采用成对搜索算法提取峰谷值,得到候选尾迹直线,并对候选尾迹进行验证,剔除虚警得到真实的尾迹,并确定尾迹的起点和方向。实验结果表明,所提算法在TerraSar-XSAR图像数据中对于船舶尾迹的检测准确率为87%。
In order to overcome the defect of Radon transform in ship wakes detection in Synthetic Aperture Radar(SAR)images,this paper proposed a wake detection algorithm based on Radon transform and wake model,which could effectively detect ship wakes in large SAR images.The algorithm used the normalized Radon transform combined with gradient to enhance the peak⁃valley values in the transform domain used the paired search algorithm to extract the peak⁃valley values to the candidate wake line,and verified the candidate wakes,removed the false alarm to get the real wakes,and determined the starting point and direction of the wakes.The experimental results show that the proposed algorithm can detect ship wakes in TerraSar⁃X SAR image data with an accuracy of 87%.
作者
王志鹤
行坤
崔宁
喻忠军
WANG Zhihe;XING Kun;CUI Ning;YU Zhongjun(Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China;School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China)
出处
《电子设计工程》
2022年第12期1-6,共6页
Electronic Design Engineering
基金
国家自然科学基金资助项目(61971026)。
