基于扩散方程和MRF的SAR图像分割

贾亚飞; 赵凤军; 禹卫东; 艾加秋

doi:10.3724/SP.J.1146.2010.00342

基于扩散方程和MRF的SAR图像分割

doi: 10.3724/SP.J.1146.2010.00342

贾亚飞^{*①② 赵凤军,},
赵凤军,
禹卫东,
艾加秋

计量
- 文章访问数: 3527
- HTML全文浏览量: 112
- PDF下载量: 1481
- 被引次数: 0
出版历程
- 收稿日期: 2010-04-01
- 修回日期: 2010-08-02
- 刊出日期: 2011-02-19

SAR Image Segmentation Based on Diffusion Equations and MRF

Jia Ya-Fei^{*①② 赵凤军
,},
Zhao Feng-Jun,
Yu Wei-Dong,
Ai Jia-Qiu

摘要

摘要: 该文提出了一种基于图像扩散方程和马尔科夫随机场(MRF)的合成孔径雷达(SAR)图像分割方法。在传统MRF算法的基础之中，引入对图像的扩散，用来平滑SAR图像中的噪声，保护图像中的边缘部分，并且加快收敛的速度。首先对输入的SAR图像进行扩散，通过MRF进行统计，得到图像中各点的后验概率，再对得到的后验概率进行扩散。与传统的MRF算法进行比较，该文的方法较好地去除了误分割斑块，减少算法的运行时间。
- SAR图像分割 /
- 偏微分方程 /
- 马尔科夫随机场(MRF) /
- 后验概率
Abstract: A novel image diffusion equations and Markov Random Field (MRF)-based segmentation method for SAR images is proposed. The method involves the image diffusion based on the traditional MRF method. It is used to smooth the noise components in the SAR image, protect the desired object boundaries, and reduce the iterative times. The input SAR image is initially smoothed. Estimates of posterior probabilities are then obtained using MRF. The posterior probability is also smoothed using diffusion. Comparing with the traditional MRF method, this method wipes off the inaccuracy classified blocks, and reduces the cost of time.
- SAR image segmentation /
- Partial differential equations /
- Markov Random Field (MRF) /
- Posterior probability

HTML全文

参考文献(1)

[1] 章毓晋. 图像工程(中册)图像分析. 北京: 清华大学出版社, 2005: 73-75. Zhang Yu-jin. Image Engineering (II)Image Analysis. Beijing: Tsinghua Publisher, 2005: 73-75. [2] Haker S, Sapiro G, and Tannenbaum A. Knowledge-based segmentation of sar data with learned priors[J].IEEE Transactions on Image Processing.2000, 9(2):299-301 [3] Papson S and Narayanan R. Modeling of target shadows for SAR image classification. 35th IEEE Applied imagery and pattern recognition workshop . Washington, 2006: 3-3. [4] Wen Xian-bin and Tian Zheng. Mixture multiscale autoregressive modeling of SAR imagery for segmentation[J].Electronics Letters.2003, 39(17):1272-1274 [5] 刘爱平, 付琨, 尤红建, 刘忠. 基于MAR-MRF的SAR图像分割方法. 电子与信息学报, 2009, 31(11): 2557-2562. Liu Ai-ping, Fu Kun, You Hong-jian, and Liu Zhong. SAR image segmentation based on multiscale autoregressive and Markov random field models[J].Journal of Electronics Information Technology.2009, 31(11):2557-2562 [6] Gaetano R, Scarpa G, and Poggi G. Hierarchical texture-based segmentation of multiresolution remote- sensing images[J].IEEE Transactions on Geoscience and Remote Sensing.2009, 47(7):2129-2141 [7] Weisenseel R, Clem Karl W, and Castanon D, et al.. Markov random field segmentation methods for SAR target chips[J].Proc. SPIE, Oriando.1999, Vol.3721:462-473 [8] 王大凯, 侯榆青, 彭进业. 图像处理的偏微分方程方法. 北京：科学出版社, 2008: 11-12. [9] Wang Da-kai, Hou Yu-qing, and Peng Jin-ye. Partial Differential Equations Methods of Image Processing. Beijing: Science Press, 2008: 11-12. [10] Perona P and Malik J. Scale-space and edge detection using anisotropic diffusion[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1990, 12(7):629-639 [11] Teo P, Sapiro G, and Wandell B. Anisotropic diffusion of posterior probabilities. IEEE Int. Conf. Image Processing, Santa Barbara, CA, 1997: 675-678. [12] 王卫卫, 冯象初. 图像处理中扩散方程的快速数值解法[J].电子与信息学报.2009, 31(7):1736-1740浏览 Wang Wei-wei and Feng Xiang-chu. Fast numerical solutions of diffusion equations in image processing[J].Journal of Electronics Information Technology.2009, 31(7):1736-1740 [13] Boccignone G, Ferraro M, and Napoletano P. Diffused expectation maximization for image segmentation[J].Electronics Letters.2004, 40(18):1107-1108 [14] 宋建设, 郑永安, 袁礼海. 合成孔径雷达图像理解与应用. 北京：科学出版社, 2008: 82-83. [15] Song Jian-she, Zheng Yong-an, and Yuan Li-hai. Synthetic Aperture Radar Image Understanding and Applications. Beijing: Science Press, 2008: 82-83.

施引文献

资源附件(0)

访问统计