聚类分析用于序列SAR干涉像对选取

该文分析了干涉像对选取过程，提出一种利用聚类分析进行序列SAR干涉像对选取的方法. 选择合适的去相干因素构建特征空间，将序列SAR影像所有干涉组合的去相干因素映射到该特征空间，从而将干涉像对选取问题转换为特征空间的聚类分析. 根据干涉像对选取原则设计合适的聚类方法对去相干因素进行聚类，聚类结果对应于符合要求的干涉像对，实现序列SAR干涉像对的选取. 实验结果表明该方法简单有效.

Cluster Analysis for Selection of Time Series Interferometric SAR Imagery

Abstract: We propose a method to select interferometric SAR pairs for time series differential SAR Interferometry (D-InSAR) by using cluster analysis. In this approach, proper decorrelation factors are selected to construct a feature space, and decorrelation factors of all possible SAR interferometric pairs are mapped to the space. Thus, interferometric pair selection is converted to a problem of feature space clustering. A cluster algorithm is developed based on the principle of interferometric pair selection. This way, selected interferometric images corresponding to the clustering result are obtained. Experimental results show that the proposed approach is simple and effective.