Improved SAR image registration algorithm based on SAR-SIFT

doi:10.13474/j.cnki.11-2246.2021.0038

Abstract

Abstract: 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 multi-source, 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.

Key words: nonlinear diffusion scale space, phase congruency, the SAR-SIFT, ROEWA, nonlinear diffusion filter

CLC Number:

P237

LI Pei, JIANG Gang, MA Qianli. Improved SAR image registration algorithm based on SAR-SIFT[J]. Bulletin of Surveying and Mapping, 2021, 0(2): 30-35,71.

References

[1] MOSER G, SERPICO S B. Unsupervised change detection from multichannel SAR data by Markovian data fusion[J]. IEEE Transactions on Geoscience & Remote Sensing, 2009, 47(7):2114-2128.
[2] ALPARONE L, BARONTI S, GARZELLI A, et al. Landsat ETM+ and SAR image fusion based on generalized intensity Modulation[J]. IEEE Transactions on Geoscience & Remote Sensing, 2004, 42(12):2832-2839.
[3] LIU M, WU Y, ZHANG P, et al. SAR target configuration recognition using locality preserving property and Gaussian mixture Distribution[J]. IEEE Geoscience & Remote Sensing Letters, 2013, 10(2):268-272.
[4] ZITOVA B, FLUSSER J. Image registration methods:a survey[J]. Image & Vision Computing, 2003, 21(11):977-1000.
[5] WANG S H,YOU H J,FU K. BFSIFT:a novel method to find feature matches for SAR image registration[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(4):649-653.
[6] SCHWIND P, SURI S, REINARTZ P, et al. Applicability of the SIFT operator to geometric SAR image registration[J]. International Journal of Remote Sensing, 2010, 31(8):1959-1980.
[7] LV W, YU W, WANG J F, et al. SAR image matching based on SIFT keypoints and multi-subregions information[C]//International Asia-pacific Conference on Synthetic Aperture Radar.[S.l.]:IEEE, 2011.
[8] WANG F, YOU H J, FU X Y. Adapted anisotropic Gaussian SIFT matching strategy for SAR registration[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(1):160-164.
[9] DELLINGER F, DELON J, GOUSSEAU Y, et al. SAR-SIFT:a SIFT-Like algorithm for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1):453-466.
[10] FAN J W, WU Y, WANG F, et al. SAR image registration using phase congruency and nonlinear diffusion-based SIFT[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(3):562-566.
[11] 刘红军, 王爽, 祝树生, 等. 一种基于各向异性尺度空间的SAR图像匹配算法[J]. 现代雷达, 2017,39(7):28-33.
[12] PERONA P, MALIK J. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1990, 12(7):629-639.
[13] WEICKERT J. Efficient image segmentation using partial differential equations and morphology[J]. Pattern Recognition, 2001, 34(9):1813-1824.
[14] KOVESI P. Image features from phase congruency[J]. Videre:Journal of Computer Vision Research, 1999, 1(3):1-26.
[15] KOVESI P. Phase congruency detects corners and edges[C]//International Conference on Digital Image Computing Techniques and Applications. Sydney:IEEE, 2003.