Main content area

Registrating large mismatching SAR images based on corners and surface extremum strategy

Yao, Guobiao, Zhang, Li, Shi, Tongguang, Deng, Kazhong
International journal of remote sensing 2019 v.40 no.9 pp. 3555-3570
algorithms, geometry, remote sensing, synthetic aperture radar
Robust and accurate registration remains a difficult task for large mismatching Synthetic Aperture Radar (SAR) images because of severe viewpoint distortion, repetitive patterns, and speckle noise. In this paper, we propose a coarse-to-fine registration method with high precision by integrating corners and Surface Extremum Strategy (SES). Our method involves three steps. First, initial corresponding points are obtained based on the complementary invariant feature matching, and then the global and local Homographic Geometry Transformations (HGTs) are estimated between image pairs. Second, we consider quasi-dense corner matches with high accuracy. The reference image is divided into quasi-dense grids from which the Förstner corners are extracted. Subsequently, we produce the coarse corresponding corners by combining the global and local HGTs using Normalized Cross Correlation (NCC), and then employ the SES of the NCC coefficients to compensate the matching deviations. Third, highly precise registration is achieved based on the matches of the second step. Experiments on four groups of large mismatching SAR images verify the effectiveness of our method, and a comprehensive comparison with existing algorithms demonstrates that the proposed method is superior in terms of the number of matches, correctness, accuracy, and spatial distribution.