Abstract
The scale-invariant feature transform (SIFT) algorithm has been widely used in remote sensing image registration. However, it may be difficult to obtain satisfactory registration precision for SAR image pairs that contain much speckle noise. In this letter, an anisotropic scale space constructed with speckle reducing anisotropic diffusion (SRAD) is introduced to reduce the influence of noise on feature extraction. Then, dual-matching strategy is utilized to obtain initial feature matches, and feature cluster analysis is introduced to refine the matches in relative distance domain, which increases the probability of correct matching. Finally, the affine transformation parameters for image registration are obtained by RANSAC algorithm. The experimental results demonstrate that the proposed method can enhance the stability of feature extraction, and provide better registration performance compared with the standard SIFT algorithm in terms of number of correct matches and aligning accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zitova, B., Flusser, J.: Image registration methods: a survey. Image Vis. Comput. 21(11), 977–1000 (2003)
Zhu, H., Ma, W.P., Hou, B., et al.: SAR image registration based on multifeature detection and arborescence network matching. J. IEEE Geosci. Remote Sens. Lett. 13(5), 706–710 (2016)
Su, J., Li, B., Wang, Y.Z.: A SAR image registration algorithm based on closed uniform regions. J. Electron. Inform. Technol. 38(12), 3282–3288 (2016)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Wang, S.H., You, H.J., Fu, K.: BFSIFT: a novel method to find feature matches for SAR image registration. IEEE Geosci. Remote Sens. Lett. 9(4), 649–653 (2012)
Chen, Y., Zhao, H.C., Chen, S., Zhang, S.N.: Image matching algorithm based on SIFT for missile-borne SAR. Syst. Eng. Electron. 38(6), 1276–1280 (2016)
Schwind, P., Suri, S., Reinartz, P., et al.: Applicability of the SIFT operator to geometric SAR image registration. Int. J. Remote Sens. 31(8), 1959–1980 (2010)
Wang, F., You, H.J., Fu, K.: Adapted anisotropic Gaussian sift matching strategy for SAR registration. IEEE Geosci. Remote Sens. Lett. 12(1), 160–164 (2015)
Fan, J.W., Wu, Y., Wang, F., et al.: SAR image registration using phase congruency and nonlinear diffusion-based SIFT. IEEE Geosci. Remote Sens. Lett. 12(3), 562–566 (2015)
Weickert, J.: A review of nonlinear diffusion filtering. In: Haar Romeny, B., Florack, L., Koenderink, J., Viergever, M. (eds.) Scale-Space 1997. LNCS, vol. 1252, pp. 1–28. Springer, Heidelberg (1997). https://doi.org/10.1007/3-540-63167-4_37
Yu, Y., Acton, S.T.: Speckle reducing anisotropic diffusion. IEEE Trans. Image Process. 11(11), 1260–1270 (2002)
Perona, P., Malik, J.: Scale space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 629–639 (1990)
Weickert, J., Romeny, B.M.H., Viergever, M.A.: Efficient and reliable schemes for nonlinear diffusion filtering. IEEE Trans. Image Process. 7(3), 398–410 (1998)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Y., Ge, Z., Su, J., Wu, W. (2018). SAR Image Registration Using Cluster Analysis and Anisotropic Diffusion-Based SIFT. In: Wang, Y., et al. Advances in Image and Graphics Technologies. IGTA 2017. Communications in Computer and Information Science, vol 757. Springer, Singapore. https://doi.org/10.1007/978-981-10-7389-2_1
Download citation
DOI: https://doi.org/10.1007/978-981-10-7389-2_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-7388-5
Online ISBN: 978-981-10-7389-2
eBook Packages: Computer ScienceComputer Science (R0)