An improved SIFT algorithm for SAR image registration

doi:10.7523/j.issn.2095-6134.2019.02.014

Abstract

Abstract: In view of the features of SAR images, we propose an improved SIFT algorithm based on the traditional SIFT algorithm combined with the ROEWA and OTSU algorithms. The algorithm firstly detects the edge region and shadow area of the image by using ROEWA and OTSU algorithms, respectively. Then, the feature points are fused by using SIFT algorithm to find the matching points and calculate the transformation matrix for image registration. Compared with the original algorithm, this method eliminates the influences of the edge response of the DoG operator and the shadow, makes the extraction of feature points more accurate, and enhances the correct matching rate, the stability of the algorithm, and the accuracy of image registration.

Key words: image registration, SIFT algorithm, ROEWA operator, OTSU algorithm

CLC Number:

TP751.1

CHI Yingpeng, LIU Chang. An improved SIFT algorithm for SAR image registration[J]. , 2019, 36(2): 259-266.

References

[1] 李孚煜, 叶发茂. 基于SIFT的遥感图像配准技术综述[J]. 国土资源遥感, 2016, 28(2):14-20.
[2] 徐颖, 周焰. SAR图像配准方法综述[J]. 地理空间信息, 2013, 11(3):63-66.
[3] Chatelain F, Tourneret J Y, Inglada J, et al. Bivariate gamma distributions for image registration and change detection[J]. IEEE Transactions on Image Processing, 2007, 16(7):1796.
[4] Argyriou V, Tzimiropoulos G. Frequency domain subpixel registration usingHOG phase correlation[J]. Computer Vision & Image Understanding, 2016, 155:70-82.
[5] Suo Z, Li Z, Bao Z. Multi-channel SAR-GMTI method robust to Coregistration Error of SAR Images[J]. Aerospace & Electronic Systems IEEE Transactions on, 2010, 46(4):2035-2043.
[6] 阿布来提·依布拉音, 王治强, 刘薇, 高慧婷. 基于Hough直线检测的深度图像配准方法[J]. 中国科学院研究生院学报, 2013, 30(1):112-116.
[7] Suri S, Reinartz P. Mutual-information-based registration of TerraSAR-X and ikonos imagery in urban areas[J]. IEEE Transactions on Geoscience & Remote Sensing, 2010, 48(2):939-949.
[8] 苏娟, 李彬, 王延钊. 一种基于封闭均匀区域的SAR图像配准方法[J]. 电子与信息学报, 2016, 38(12):3282-3288.
[9] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[10] Hossein-Nejad Z, Nasri M. An adaptive image registration method based on SIFT features and RANSAC transform[J]. Computers & Electrical Engineering, 2016. 62:524-537.
[11] 王茜, 宁纪锋, 曹宇翔,等. 基于SIFT算法的无人机遥感图像拼接技术[J]. 吉林大学学报(信息科学版), 2017, 35(2):188-197.
[12] Zhong H, Zhang J, Liu G. Robust polarimetric SAR despeckling based on nonlocal means and distributed Lee filter[J]. IEEE Transactions on Geoscience & Remote Sensing, 2014, 52(7):4198-4210.
[13] Fjørtoft R, Lopès A, Marthon P, et al. An optimal multiedge detector for SAR image segmentation[J]. IEEE Transactions on Geoscience & Remote Sensing, 1998, 36(3):793-802.
[14] 刘夯, 何政伟, 赵银兵, 等. SAR图像ROEWA边缘检测器的改进[J]. 遥感学报, 2017, 21(2):273-279.
[15] Bangare S L, Dubal A, Bangare P S, et al. Reviewing Otsu's method for image thresholding[J]. International Journal of Applied Engineering Research, 2015, 10(9):21777-21783.
[16] 赵夫群, 周明全, 耿国华, 等. 基于GA-Otsu法的图像阈值分割及定量识别[J]. 吉林大学学报(工学版), 2017, 47(3):959-964.
[17] Liu X, Tian Z, Lu Q, et al. A new affine invariant descriptor framework in shearlets domain for SAR image multiscale registration[J]. AEU-International Journal of Electronics and Communications, 2013, 67(9):743-753.