An Unsupervised Approach Based on Geometrical Structures to Automatic Change Detection in Multitemporal SAR Images

CHANG Bao; ZHANG Gong

您当前的位置：

首页 >

文章列表页 >

An Unsupervised Approach Based on Geometrical Structures to Automatic Change Detection in Multitemporal SAR Images

更新时间：2025-07-16

- An Unsupervised Approach Based on Geometrical Structures to Automatic Change Detection in Multitemporal SAR Images
- Acta Electronica Sinica Vol. 39, Issue 9, Pages: 2125-2129(2011)
- 作者机构：
  
  南京航空航天大学电子信息工程学院,江苏,南京,210016
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP751.1
- Published：2011
- 稿件说明：
移动端阅览
CHANG Bao, ZHANG Gong. An Unsupervised Approach Based on Geometrical Structures to Automatic Change Detection in Multitemporal SAR Images[J]. Acta Electronica Sinica, 2011, 39(9): 2125-2129.
DOI：

CHANG Bao, ZHANG Gong. An Unsupervised Approach Based on Geometrical Structures to Automatic Change Detection in Multitemporal SAR Images[J]. Acta Electronica Sinica, 2011, 39(9): 2125-2129. DOI：

摘要

传统的基于统计特性的SAR图像变化检测方法

易受成像条件的影响而误差很大.本文针对图像内在几何结构

提出了一种无监督SAR图像变化检测算法.通过模糊微分构造描述图像局部特征的近似完整数据集

并充分利用图像局部邻域信息和空间相关性

构造深入描述图像结构化信息的特征矢量空间

最后通过基于模拟退火的

均值(SAKM)聚类算法

实现图像变化区域与非变化区域的分类.实验证明

本文方法不仅能够很好的检测出图像的轮廓变化和图像的区域变化

而且对噪声及配准精度均具有很好的鲁棒性.

Abstract

Traditional statistically-based SAR image change detection is usually limited by imaging conditions.We propose an unsupervised change detection algorithm based on the image inherent geometrical structures.Firstly

an approximate complete data set is constructed to describe the image local features via fuzzy derivatives

and then a feature vector space is made to represent the image inherent structures using image local neighborhood information and spatial correlation.Finally the change map is produced by simulated annealing-based

-means (SAKM) clustering arithmetic.Experimental results show great detection performance both in contour and region.Besides

it is robust to noises and registration.

关键词

Keywords

references

Views

1628

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Refocusing for Three-Dimensional Rotating Ship Targets in SAR Images Based on Minimum Entropy Criteria and Generative Adversarial Network

Edge Guided and Dynamically Deformable Transformer Network for Remote Sensing Images Change Detection

MAFNet: A Multi-Path Asymmetric Fusion Network for Metric-Based Change Detection in High-Resolution Remote Sensing Images

Active Jamming Suppression for SAR Images Based on Self-Supervised Complex-Valued Deep Learning

SAR Recognition Method of Ship Targets for SAR Based on M3Net

Related Author

HUA Qing-long

ZHANG Yun

REN Hang

JIANG Yi-cheng

XU Dan

LEI Tao

ZHAI Yu-jie

XU Ye-tong

Related Institution

School of Electronics and Information Engineering， Harbin Institute of Technology

Shaanxi Joint Laboratory of Artificial Intelligence， Shaanxi University of Science and Technology

School of Electronic Information and Artificial Intelligence， Shaanxi University of Science and Technology

Key Laboratory of Collaborative intelligent Systems， Ministry of Education， Xidian University

School of Geodesy and Geomatics， Wuhan University

⁰