基于FCM直线拟合与Radon变换的SAR舰船图像分割  

SAR Ship Image Segmentation Based on FCM Straight Line Fitting and Radon Transform

作　　者：贺顺[1] 李丹阳 刘祥熹 HE Shun;LI Danyang;LIU Xiangxi(College of Communication and Information Engineering,Xi'an University of Science and Technology,Xi'an 710600)

机构地区：[1]西安科技大学通信与信息工程学院,西安710600

出　　处：《舰船电子工程》2025年第2期39-44,93,共7页Ship Electronic Engineering

基　　金：国家自然科学基金项目“高动态飞行器分布式异形天线阵列信号处理关键技术研究”(编号:62071481)资助。

摘　　要：针对合成孔径雷达舰船图像分割结果损失舰船几何特征的问题,提出一种基于FCM直线拟合与Radon变换的SAR舰船图像的分割方法。首先,利用改进的FCM将舰船目标与海洋背景进行初始分割,然后对分割结果进行最小距离直线拟合,得到舰船目标的方位角,再对图像进行Radon变换分割出目标,最后对Radon变换后的图像进行形态学优化。实验结果表明,相较于传统分割算法,该算法域间差异性提高至0.996 060,域内一致性提高至0.679 505,形状复杂度降低至1.990 942,能够有效改善SAR舰船目标的分割效果,增强舰船目标分割的稳定性,对海上舰船目标的识别与分类具有重要意义。Aiming at the problem that synthetic aperture radar(SAR)ship image segmentation results lose ship geometry features,a new segmentation method of SAR ship image based on FCM line fitting and Radon transform is proposed.Firstly,the improved fuzzy C-means clustering algorithm is used to initially segment the ship target and the ocean background,and then the minimum distance linear fitting of the segmentation results is carried out to obtain the ship target's azimuth angle,and then the image is segmented by Radon transform.Finally,morphological optimization is carried out on the image after Radon transform.The experimental results show that compared with the traditional segmentation algorithm,the difference between the algorithms can be increased to 0.996 060.Intra-domain consistency is increased to 0.679 505.The shape complexity is reduced to 1.990 942,which can effectively improve the segmentation effect of SAR ship target and enhance the stability of ship target segmentation,which is of great significance for the recognition and classification of Marine ship target.

关 键 词：合成孔径雷达 图像分割 舰船目标 直线拟合 RADON变换 

分 类 号：TN959[电子电信—信号与信息处理]