非下采样轮廓波变换(non-subsampled contourlet transform,NSCT)和变化向量分析法(change vector analysis,CVA)在高分辨率遥感影像变化检测中,会因不同地物的变化幅度有显著差异,而在单一阈值下无法保证较高的检测精度.为此,文章在后验概率空间变化向量分析(change vector analysis in posterior probability space,CVAPS)的框架下,提出了一种基于模糊C均值聚类(fuzzy C-means,FCM)和简单贝叶斯网络(simple Bayesian network,SBN)的NSCT变化检测方法(FCM-SBN-CVAPS-NSCT).该方法首先将FCM与SBN耦合,计算出后验概率变化强度图;之后,通过NSCT将后验概率变化强度图分解为不同尺度和方向的子图,通过保留高频子图中的细节并消除噪声,优化了重构后的后验概率变化强度图,实现了后验概率空间下的多尺度、多方向的变化检测,最终提高了变化检测的精度.实验结果表明,所提方法在3个研究区中得到的Kappa系数比FCM-SBN-CVAPS分别高出了 0.100 9,0.056 6和0.067 4,具有一定的优越性.
NSCT-based change detection for high-resolution remote sensing images under the framework of change vector analysis in posterior probability space
In the change detection for high-resolution remote sensing images,non-subsampled contourlet transform(NSCT)and change vector analysis(CVA)cannot ensure high detection accuracies under single thresholds due to significantly different changes in surface features.Hence,under the framework of change vector analysis in posterior probability space(CVAPS),this study proposed a NSCT-based change detection method combining fuzzy C-means(FCM)clustering and a simple Bayesian network(SBN):the FCM-SBN-CVAPS-NSCT method.First,the proposed method coupled FCM with an SBN to generate a change intensity map in posterior probability space.Then,the change intensity map was decomposed into submaps of different scales and directions through NSCT.The reconstructed change intensity map was optimized by preserving the details and eliminating noise in the high-frequency submaps.Finally,the multi-scale and multi-directional change detection in posterior probability space was achieved,enhancing the change detection accuracy.As indicated by the experimental results,the Kappa values obtained by the proposed method for three study areas were 0.100 9,0.056 6,and 0.067 4 higher than those derived from the FCM-SBN-CVAPS method,demonstrating certain superiority.
simple Bayesian networkfuzzy C-means clusteringchange vector analysis in posterior probability spacenon-subsampled contourlet transform
国家科技期刊平台
NSTL
万方数据
