结合局部频率估计的小波域InSAR相位滤波新方法

Novel InSAR phase filtering method in wavelet domain integrated with local frequency estimation

干涉相位噪声的存在直接影响相位解缠的效果及最终干涉测量的精度。针对这一问题,本文提出了一种结合局部频率估计的小波域干涉合成孔径雷达(interferometric synthetic aperture radar,InSAR)相位滤波方法。根据局部频率估计可以判断出干涉相位小波系数中包含有用信息的子带。结合VisuShrink和NeighShrink两种小波阈值收缩方法分别具有去噪效果好和细节保持能力强的特点,对有用信息所在子带的小波系数利用NeighShrink方法进行阈值收缩,而对其他子带的小波系数则利用VisuShrink方法进行阈值收缩,从而尽可能地滤除噪声,同时保持干涉条纹的细节信息不被破坏。仿真和实测数据实验验证了本文提出的滤波方法的有效性。

Phase noise in the interferogram directly affects the result of phase unwrapping and the precision of interferometirc measurement. A novel approach combining the local frequency estimation with wavelet trans- form is presented to reduce interferometric phase noise for interferometric synthetic aperture radar （InSAR）. According to the local frequency estimation result, the subband of wavelet coefficients containing useful infor- mation can be found out. Based on the fact that the VisuShrink method has effective noise reduction ability and the NeighShrink method performs well in detail preservation, the wavelet coefficients containing useful informa- tion are shrunk by the NeighShrink method while the others are shrunk by the VisuShrink method. As a result, the noisy interferogram can be efficiently filtered without destroying the fringes. The experiments using the sim- ulated data and the real data demonstrate the validity of the proposed method.