Building Segmentation from High-Resolution SAR Images Based on Improved Markov Random Field

FU Xing-yu; YOU Hong-jian; FU Kun

doi:10.3969/j.issn.0372-2112.2012.06.012

您当前的位置：

首页 >

文章列表页 >

Building Segmentation from High-Resolution SAR Images Based on Improved Markov Random Field

更新时间：2025-07-16

- Building Segmentation from High-Resolution SAR Images Based on Improved Markov Random Field
- Acta Electronica Sinica Vol. 40, Issue 6, Pages: 1141-1147(2012)
- 作者机构：
  
  1. 中国科学院空间信息处理与应用系统技术重点实验室,北京,100190
  2. 中国科学院电子学研究所,北京,100190
  3. 中国科学院研究生院,北京,100049
  4. 中国科学院空间信息处理与应用系统技术重点实验室北京,100190
  5. 中国科学院电子学研究所北京,100190
  6. 中国科学院研究生院北京,100049
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.40871209)
- DOI：10.3969/j.issn.0372-2112.2012.06.012
  CLC： TP753TN959.7
- Published：2012
- 稿件说明：
移动端阅览
FU Xing-yu, YOU Hong-jian, FU Kun. Building Segmentation from High-Resolution SAR Images Based on Improved Markov Random Field[J]. Acta Electronica Sinica, 2012, 40(6): 1141-1147.
DOI：

FU Xing-yu, YOU Hong-jian, FU Kun. Building Segmentation from High-Resolution SAR Images Based on Improved Markov Random Field[J]. Acta Electronica Sinica, 2012, 40(6): 1141-1147. DOI： 10.3969/j.issn.0372-2112.2012.06.012.

摘要

提出了一种基于改进Markov随机场模型的高分辨率SAR (Synthetic Aperture Radar

合成孔径雷达)图像建筑物分割算法.针对高分辨率SAR图像信噪比低和建筑物复杂纹理特性的特点

采用多尺度Markov随机场模型的最大似然准则方法获取图像的初始分割

并在传统Markov邻域能量模型基础之上提出一种新的基于Gabor纹理相似度的邻域势函数模型

采用ICM (Iterative Conditional Model

迭代条件模型)算法进行建筑物分割.多组实际高分辨率SAR图像的实验结果表明

与传统MRF算法等方法相比

本文方法具有更高的分割正确率

同时建筑物边界更为清晰平滑

分割效果较好.

Abstract

An approach was proposed for building segmentation from high resolution SAR (Synthetic Aperture Radar) images based on an improved Markov random field (MRF) model.Aiming at the property of low SNR (Signal to Noise Ratio) of SAR images and the complexity of building textures

we obtained the initial segmentation using the maximum likelihood (ML) algorithm based on the multi-scale MRF model and involved the Gabor similarity between pixels based on the traditional MRF potential function

and employed the ICM (Iterative Conditional Model) algorithm to implement the segmentation.The experimental results on several real SAR images show that the proposed approach performs better than traditional methods in the segmentation accuracy

and building boundaries are clearly obtained by the proposed approach.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Facial Feature Points Extraction in Color Images

A Target Feature Extraction Method Based on SEEMD in High-Resolution SAR Image

Related Author

WU Zheng

ZHOU Yue

DU Chun-hua

YUAN Quan

GE Xin-liang

LOU Jun

JIN Tian

ZHOU Zhi-min

Related Institution

Institute of Image Processing and Pattern Recognition,Shanghai JiaoTong University

Shanghai Branch of Huaxia Bank

Institute of Image Processing and Pattern RecognitionShanghai Jiao Tong UniversityShanghai 200240China

Shanghai Branch of Huaxia BankShanghai 200120China

College of Electronic Science and Engineering, National University of Defense Technology

⁰