一种基于马尔可夫随机场的SAR图像分割新方法
doi: 10.3724/SP.J.1146.2005.01359
A Novel SAR Image Segmentation Method Based on Markov Random Field
-
摘要: 该文提出了一种基于马尔可夫随机场(MRF)的合成孔径雷达(SAR)图像分割新方法。在传统MRF的邻域基团势函数基础上，引入了图像邻域中各个像素的强度差值以及像素之间的距离因子，使SAR图像中空间上下文信息得到了更加充分的利用。根据贝叶斯定理将图像分割问题转化为最大后验概率的求取问题，运用迭代条件模型(ICM)算法求得最大后验概率的解。在实验中，将该文提出的方法、传统上使用ICM以及模拟退火(SA)优化方法的MRF分割运用于模拟的SAR图像以及真实SAR图像。比较结果证明，该文的方法在误分率以及抗噪性上更具优势。
-
关键词:
- SAR图像;图像分割;势函数;最大后验
Abstract: A novel Markow Random Field(MRF)-based segmentation method for SAR images is proposed. The method involves the intensity differences and the distances between pixels based on the traditional MRF potential function. It utilizes more spacial information of SAR image in the potential function model. The segmentation issue is transformed to the Maximum A Posteriori (MAP) by Beyes theorem. Finally, the Iterative Conditional Model (ICM) is employed to find out the solution of MAP problem. In the experiments, the method is compared with the traditional MRF segmentation method using ICM and simulate annealing, the results showed that this method is better than the traditional MRF one both in noise filtering and miss-classification ratio. -
Franceschetti G and Lanari R. Synthetic Aperture Radar Processing. New York: CRC Press, 1999: 3-10.[2]U laby F T and Kouyate F. Texture information in SAR images[J].IEEE Trans. on Geosc and Remote Sensing.1986, 24(2):235-245[3]Caves R and Quegan S. Qualitative comparision of the performance of SAR segmentation algorithms[J].IEEE Trans. on Image Processing.1998, 7(11):1534-1546[4]Lee J. Speckle analysis and smoothing of synthetic aperture radar images[J].Computer Graphics and Image Processing.1981, 17(1):24-32[5]Descombes X and Moctezuma M. Coastline detection by a Markovian segmentation on SAR images. Signal Processing, 1996, (55): 123-132.[6]Chellappa R and Jain A. Markov Random Fields: Theory and Application. New York: Academic Press, 1993: 13-25.[7]Melas D and Wilson S. Double Markov random fields and Bayesian image segmentation[J].IEEE Trans. on Signal Processing.2002, 50:357-365[8]张翠, 郦苏丹, 王正志. 基于MRF的SAR图像分割方法. 遥感技术与应用, 2001, 16(1): 66-68. Zhang Cui, Li Su-dan, and Wang Zheng-zhi. SAR image segmentation based on Markov random field model. Remote Sensing Technology and Application, 2001, 16(1): 66-68.[9]Lankoande O, Hayat M M, and Santhanam B. Speckle reduction of SAR images using a physically based Markov random field model and simulated annealing[J].Proc. of SPIE.2005, Vol. 5808:210-221 -
计量
- 文章访问数: 3338
- HTML全文浏览量: 100
- PDF下载量: 2008
- 被引次数: 0
下载:
