结合邻域信息自适应优化的SAR图像变化检测  

SAR image change detection based on adaptive optimization of neighborhood information

作　　者：朱拂晓 董张玉[1,2,3] 杨学志 ZHU Fuxiao;DONG Zhangyu;YANG Xuezhi(College of Computer and Information,Hefei University of Technology,Hefei 230031,China;Anhui Province Key Laboratory of Industry Safety and Emergency Technology,Hefei 230031,China;Anhui Province Laboratory of Intelligent Interconnection System,Hefei 230031,China;College of Software,Hefei University of Technology,Hefei 230031,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230031 [2]工业安全与应急技术安徽省重点实验室,合肥230031 [3]智能互联系统安徽省实验室,合肥230031 [4]合肥工业大学软件学院,合肥230031

出　　处：《智能计算机与应用》2022年第7期20-24,34,共6页Intelligent Computer and Applications

摘　　要：为提高SAR图像变化检测的精度,本文提出了一种邻域信息自适应优化及差异图融合的SAR图像变化检测算法。该算法首先根据邻域信息异质性计算像素点的自适应窗口生成自适应的对数均值比差异图像,充分抑制噪声影响;其次,将其与差值图加权融合,保留了图像的细节部分;最后,利用基于邻域隶属度约束的FCM聚类算法对融合后的差异图像进行分类。实验结果表明,该方法有效抑制了噪声对结果的影响,提高了变化检测的精度。To improve the accuracy of SAR image change detection, an algorithm of change detection based on adaptive optimization of neighborhood information and difference image fusion is proposed. The algorithm first constructs an adaptive log-mean ratio difference image according to the heterogeneity of neighborhood information to fully suppress the effect of noise. Then the image is fused with subtraction difference image. The details of the image are preserved. Finally, the FCM clustering algorithm based on neighborhood membership constraint is used to classify the fused difference image. Experimental results show that this method can effectively restrain the impact of noise on the results and improve the accuracy of change detection.

关 键 词：SAR图像 变化检测 自适应窗口 差异图融合 FCM聚类 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]