SAR Image Registration Using Phase Congruency and Nonlinear Diffusion-Based SIFT
- 9 September 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 12 (3), 562-566
- https://doi.org/10.1109/lgrs.2014.2351396
Abstract
The scale-invariant feature transform (SIFT) algorithm has been widely applied to optical image registration. However, mostly because of multiplicative speckle noise, SIFT has a limited performance when directly applied to synthetic aperture radar (SAR) image. In this letter, a novel SAR image registration method is proposed, which is based on the combination of SIFT, nonlinear diffusion, and phase congruency. In our proposed algorithm, the multiscale representation of a SAR image is generated by nonlinear diffusion, since it better preserves edges in the image as opposed to Gaussian smoothing, which is used in the original SIFT. To reduce the influence of multiplicative speckle noise, the ratio of exponential weighted average operator is used to compute the gradient information in the construction of nonlinear diffusion scale space. Moreover, phase congruency information is utilized to remove the erroneous keypoints within the initial keypoints. Experimental results on multipolarization, multiband, and multitemporal SAR images indicate that our algorithm can improve the match performance compared to the SIFT-based method, which leads to a subpixel accuracy for all the tested image pairs.Keywords
Funding Information
- Natural Science Foundation of China (61272281, 61271297)
- National Key Basic Research and Development Program of China (973) (2011CB707001)
- National Defense Foundation of China (9140A07020913DZ01001)
- Fundamental Research Funds for the Central Universities (7214314702, 7214588502)
This publication has 12 references indexed in Scilit:
- SAR-SIFT: A SIFT-like algorithm for applications on SAR imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- A Vector SIFT Detector for Interest Point Detection in Hyperspectral ImageryIEEE Transactions on Geoscience and Remote Sensing, 2012
- BFSIFT: A Novel Method to Find Feature Matches for SAR Image RegistrationIEEE Geoscience and Remote Sensing Letters, 2011
- Automatic Image Registration Through Image Segmentation and SIFTIEEE Transactions on Geoscience and Remote Sensing, 2011
- Applicability of the SIFT operator to geometric SAR image registrationInternational Journal of Remote Sensing, 2010
- Measures for an Objective Evaluation of the Geometric Correction Process QualityIEEE Geoscience and Remote Sensing Letters, 2009
- ARRSI: Automatic Registration of Remote-Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2007
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- An optimal multiedge detector for SAR image segmentationIEEE Transactions on Geoscience and Remote Sensing, 1998
- Efficient and reliable schemes for nonlinear diffusion filteringIEEE Transactions on Image Processing, 1998