系统工程与电子技术 ›› 2019, Vol. 41 ›› Issue (8): 1726-1734.doi: 10.3969/j.issn.1001-506X.2019.08.08

• 传感器与信号处理 • 上一篇    下一篇

基于改进FCM与MRF的SAR图像分割

韩子硕, 王春平   

  1. 陆军工程大学石家庄校区电子与光学工程系, 河北 石家庄 050003
  • 出版日期:2019-07-25 发布日期:2019-07-25

SAR image segmentation based on improved FCM and MRF

HAN Zishuo, WANG Chunping   

  1. Department of Electronic and Optical Engineering, Shijiazhuang Campus, Army Engineering University, Shijiazhuang 050003, China
  • Online:2019-07-25 Published:2019-07-25

PDF (PC)

摘要：

合成孔径雷达(synthetic aperture radar, SAR)图像相干斑点噪声强,缺乏背景与目标先验知识,导致分割困难。针对以上问题,提出了基于改进模糊C均值聚类(fuzzy C-means clustering,FCM)与马尔可夫随机场(Markov random field,MRF)的分割算法。首先,利用自适应非局部均值滤波和基于直方图峰值点的初始聚类中心选定规则,提升快速FCM算法效率;然后分别用改进FCM算法与MRF对SAR图像进行分割,并通过构建联合隶属度矩阵自适应选择最优分割区域;最后利用形态学操作对结果进行优化。实验表明,所提算法具有较好的抗噪性能,能够快速有效地分割多类SAR图像。

关键词: 模糊C均值聚类, 马尔可夫随机场, 非局部均值, 图像分割

Abstract:

The problems of strong coherent speckle noise and the lack of prior knowledge of background and targets, make segmentation difficult in synthetic aperture radar(SAR) images. A segmentation algorithm based on improved fuzzy C-means (FCM) clustering and Markov random field (MRF) is proposed. Firstly, the efficiency of fast FCM is improved by the adaptive nonlocal mean filter and the initial clustering center selection rule based on histogram peak points. Secondly, the SAR image is segmented by improved FCM and MRF respectively, and the optimal segmentation regions are adaptively selected by constructing the joint membership matrix. Finally, the final segmentation result is optimized by morphological operations. The experimental results show that the proposed algorithm has better antinoise performance and can segment multiclass SAR images quickly and efficiently.

Key words: fuzzy C-means clustering (FCM), Markov random field (MRF), non-local mean, image segmentation

京ICP备11035014号-5
版权所有 © 2019 北京航天情报与信息研究所《系统工程与电子技术》编辑部
通讯地址：北京市142信箱32分箱《系统工程与电子技术》编辑部(100854)
电　话：(010)68388406/68386014    E-mail：xtgcydzjs@126.com(系统工程与电子技术)/jseeoffice@126.com(JSEE)
本系统由北京玛格泰克科技发展有限公司设计开发