Please wait a minute...
浙江大学学报(工学版)
J4  2012, Vol. 46 Issue (10): 1810-1815    DOI: 10.3785/j.issn.1008-973X.2012.10.012
    
Fast implementation of SAR image segmentation using
Markov random fields
LI Guang-ting1, 2, YU Wei-dong1
1. Department of Space Microwave Remote Sensing System, Institute of Electronics, Chinese Academy of Sciences,
Beijing 100190, China; 2. Graduate University of the Chinese Academy of Sciences, Beijing 100049, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A new image segmentation flow using Markov random fields (MRF) was proposed in order to solve the problem of the low computation efficiency with the general synthetic aperture radar (SAR) image segmentation using MRF. The method takes all the edge pixels of marking map in the whole image as operation objects. The false segmentation probability caused by only processing the edges of marking map was analyzed, and the application of proposed flow in diffusion MRF was also discussed. The analysis and experimental results of MSTAR image segmentation show that the method can greatly shorten the calculation time of the general implementation without loss of segmentation precision, and can obtain better segmentation results by combining with other advanced techniques.

Published: 01 October 2012
CLC:  TN 957.5  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

LI Guang-ting, YU Wei-dong. Fast implementation of SAR image segmentation using
Markov random fields. J4, 2012, 46(10): 1810-1815.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2012.10.012     OR     http://www.zjujournals.com/eng/Y2012/V46/I10/1810


马尔可夫随机场SAR图像分割的快速实现技术

针对用马尔可夫随机场(MRF)进行合成孔径雷达(SAR)图像分割的传统实现方式计算效率低的问题,提出以图像整体为操作对象并与标记图的边缘检测相结合的MRF图像分割快速实现方法.分析只针对标记图边缘像素进行处理带来错误分割的概率,将提出方法应用到扩散MRF分割中.理论分析及实验表明：与原实现方式相比,提出算法大大提高了单次迭代的速度,并可应用到一些先进的MRF分割算法中.

［1］ OLIVER C, QUEGAN S. Understanding synthetic aperture radar images ［M］. Norwood: Artech House, 1998: 75-86.
［2］ 李旭超,朱善安.图像分割中的马尔可夫随机场方法综述 ［J］.中国图像图形学报,2007, 12(5): 789-798.
LI Xuchao, ZHU Shanan. A survey of the Markov random field method for image segmentation ［J］. Journal of Image and Graphics, 2007, 12(5): 789-798.
［3］ GLEICH D, DATCU M. Waveletbased despeckling of SAR images using GaussMarkov random fields ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12): 4127-4143.
［4］ GLEICH D, DATCU M. Waveletbased SAR images despeckling and information extraction, using particle filter ［J］. IEEE Transactions on Image Processing, 2009, 18(10): 2167-2184.
［5］ MOLINA D P, GLEICH D, DATCU M. Gibbs random field models for modelbased despeckling of SAR Images ［J］. IEEE Geoscience and Remote Sensing Letters, 2010, 7(1): 73-77.
［6］ GLEICH D, KSENEMEN K, DATCU M. Despeckling of TerraSARX data using secondgeneration wavelets ［J］. IEEE Geoscience and Remote Sensing Letters, 2010, 7(1): 68-72.
［7］  宋晓峰,王爽,刘芳.基于区域MRF和贝叶斯置信传播的SAR图像分割 ［J］.电子学报,2010, 38(12): 2810-2815.
SONG Xiaofeng, WANG Shuang, LIU Fang. SAR image segmentation using Markov random field based on regions and Bayes Belief Propagation ［J］. ACTA Electronica Sinica, 2010, 38(12): 2810-2815.
［8］ FELZENSZWALB P, MCALLESTER D, RAMANAN D. A discriminatively trained, multiscale, deformable part model ［C］∥IEEE Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008: 1-8.
［9］ 贾亚飞,赵凤军,禹卫东.基于扩散方程和MRF的SAR图像分割［J］.电子与信息学报,2011,33(2): 363-368.
JIA Yafei, ZHAO Fengjun, YU Weidong. SAR image segmentation based on diffusion equations and MRF ［J］. Journal of Electronics and Information Technology, 2011, 33(2): 363-368.
［10］ LEI X G, LI Y, ZHAO N. Fast segmentation approach for SAR image based on simple Markov random field ［J］. Journal of Systems Engineering and Electronics, 2010, 21(1): 31-36.
［11］ STAN Z L. Markov random field modeling in image analysis ［M］. London: Springer, 2009: 21-27.
No related articles found!