摘要
为尽可能多地消除遥感图像变化检测过程中"伪变化"信息的影响,获得比较客观的感兴趣区域变化检测结果,针对遥感图像中SAR图像的特点,提出一种混合的SAR图像变化检测算法。对已配准好的图像进行Frost滤波,用邻域比值的方法构造差异图,对得到的差异图进行非下采样轮廓波变换(NSCT),对变换得到的高频子带和低频子带分别处理,用模糊C均值(FCM)聚类算法得到变化检测的结果。实验结果表明,该算法模型很好地保留了图像变化区域的细节,提高了变化检测准确性。
To get rid of the influence of pseudo-change as much as possible and obtain more obj ective test results in the regions of variation,a hybrid SAR image change detection algorithm was presented based on the characteristics of SAR image.Firstly,the images registered well were treated by filtering and then the difference image was constructed using the method of neighborhood ratio and processed using the method of nonsubsampled Contourlet transform （NSCT）.The high-frequency and low-frequency sub-bands were handled.The results of change detection were obtained using the fuzzy C-means （FCM）clustering algorithm. Experimental results show that the proposed algorithm not only retains the details of the change region,but also improves the change detection accuracy.
出处
《计算机工程与设计》
北大核心
2015年第5期1256-1259,1273,共5页
Computer Engineering and Design
基金
教育部促进与美大地区科研合作与高层次人才培养基金项目(2012-1738)
关键词
遥感图像
邻域比值
非下采样轮廓波变换
低频子带
模糊C均值聚类算法
remote sensing image
neighborhood ratio
nonsubsampled Contourlet transform
low-frequency sub-bands
fuzzy C-means clustering algorithm
