基于SAR-SIFT改进的SAR图像配准

合成孔径雷达(SAR)图像配准时,由于受到乘性散斑影响,匹配算法的性能受到限制.SAR-SIFT使用ROEWA算子代替差分算法计算梯度,对SAR图像的散斑具有一定的稳健性.为了进一步抑制散斑噪声,本文提出了基于SAR-SIFT改进的SAR图像配准算法.利用非线性扩散滤波生成SAR图像的非线性扩散尺度空间,在非线性尺度空...

Improved SAR image registration algorithm based on SAR-SIFT

During SAR image registration,the performance of the matching algorithm is limited due to the impact of multiplicative speckle.SAR-SIFT uses ROEWA operator instead of difference algorithm to calculate the gradient,which is robust to the speckle of SAR images.In order to further suppress speckle noise,an improved algorithm based on SAR-SIFT is proposed in this paper,which combines nonlinear diffusion filtering and phase congruency.In the proposed algorithm,the nonlinear diffusion filter is used to generate the nonlinear diffusion scale space of the SAR image,and the corresponding SAR-Harris function is calculated on different scale layers in the nonlinear diffusion scale space.To make the nonlinear diffusion scale space robust to speckle noise,the gradient information in the construction process of the nonlinear diffusion scale space is also calculated using the ROEWA operator.In addition,the phase congruency information is used to remove erroneouspoints caused by speckle in the initial key points.Experimental results on multisource,multi-polarization,and multi-temporal SAR images indicate that our improved algorithm is more robust to speckle noise and improve the match performance compared to the SAR-SIFT algorithm.