摘要
为了提高SAR图像分割精度,提出在以灰度共生矩阵产生的纹理统计量为特征所生成的图像上,同时考虑SAR图像像素间空间分布特征和局部灰度均值和方差等统计量给出多分辨双Markov框架下的GAR模型,采用多分辨MPM的参数估计方法及对应的无监督分割算法,对SAR图像进行纹理分割。实验结果表明该方法用于一些高分辨SAR图像,与基于灰度图像上的多分辨双Markov-GAR模型纹理分割相比,在分割精度上能降低分割时的错分率。
This paper presents a new method for segmentation of synthetic aperture radar(SAR) images.We take into account spatial distributed characters between pixels of SAR images as well as the local means and variances statistics of gray level,a Gaussian autoregressive (GAR) model under a multiresolution pariwise Markov framework can be proposed based on texture feature images witch come from gray level co-occurrence probability statistics.For texture segmentation of SAR images,using the multiresolution maximizati...
出处
《宇航学报》
EI
CAS
CSCD
北大核心
2007年第3期677-681,701,共6页
Journal of Astronautics
基金
国家自然科学基金(60375003)
航空科学基金(03153059)
关键词
SAR图像
灰度共生矩阵
双Markov模型
多分辨MPM
纹理分割
SAR image
Gray level co-occurrence matrices
Pairwise markov random field model
Multiresolution MPM
Texture segmentation