结合强度和相干信息的多阈值SAR影像变化检测  

Multi-thresholds Based Change Detection of SAR Images by Combining the Intensity and Coherence Information

作　　者：刘妍[1] 徐德伟[1] 李立[1] 黄平平[2] 杨文[1] 

机构地区：[1]武汉大学电子信息学院,武汉430072 [2]内蒙古工业大学雷达技术研究所,呼和浩特010051

出　　处：《信号处理》2015年第11期1531-1538,共8页Journal of Signal Processing

基　　金：国家自然科学基金(61271401;61461040);内蒙古自治区科技计划项目(20140155);内蒙古高等学校青年科技英才支持计划(NJYT-14-B09)项目资助课题

摘　　要：本文研究了联合SAR影像强度与相干信息的多阈值融合变化检测技术。针对SAR影像强度和相干信息各自统计分布特点,首先通过选定合适的统计分布模型分别对强度和相干信息进行统计分布拟合,并以Jeffrey距离为差异度量获取强度和相干信息的差异图。然后利用三种阈值方法分别对两者的差异图进行阈值分割,获得多幅初步的变化结果图。最后利用马尔科夫随机场进行融合,得到最终的变化检测结果。实验结果表明该融合策略可以获得比单一阈值法更为稳定的变化检测结果。In this paper,we investigate the change detection techniques for SAR images by using the statistical distribution models of the intensity and coherence information with a multi-thresholds fusion method. According to the statistical characteristics of the intensity and coherence information of SAR images,we first select suitable distributions to model the intensity and coherence information respectively,and use Jeffrey distance as a difference metric to obtain difference maps. Then,we employ three different thresholding based segmentation methods to obtain preliminary results of change detection. Finally,we use Markov Random Field to fuse multiple difference maps for achieving the final result. Experimental results show that our method can obtain more stable results compared with the single threshold based methods.

关 键 词：合成孔径雷达图像 变化检测 统计分布 多阈值融合 

分 类 号：TN958[电子电信—信号与信息处理]