基于小波变换的多时相SAR图像变化检测技术

Multi-temporal SAR Image Change Detection Technique Based on Wavelet Transform

提出基于小波变换的双阈值(TWT)SAR图像变化检测算法。采用期望最大化(EM)算法产生双阈值,可以区分像素发生变化的类型(如变化区域增强类和变化区域减弱类)或变化等级。用SAR图像数据进行实验,结果表明该方法有效。

A new two-threshold wavelet transform（TWT） SAR image change detection algorithm is proposed.The TWT algorithm uses the expectation maximum（EM） algorithm to produces two thresholds,so it can distinguish the changed classes（such as the enhanced change region and the weakened change region） or the changed grades.Finally,some SAR images are used to test the proposed method and the results verify that the method is effective.