Feature Matching for SAR and Optical Images Based on Gaussian-Gamma-shaped Edge Strength Map

• Main Authors: CHEN Min, ZHU Qing, ZHU Jun, XU Zhu, HUANG Lanxin
• Format: Article
• Language: zho
• Published: Surveying and Mapping Press 2016-03-01
• Series: Acta Geodaetica et Cartographica Sinica
• Subjects: SAR image; image matching; phase congruency; Gaussian-Gamma-shaped edge strength map
• Online Access: http://html.rhhz.net/CHXB/html/2016-3-318.htm

A matching method for SAR and optical images, robust to pixel noise and nonlinear grayscale differences, is presented. Firstly, a rough correction to eliminate rotation and scale change between images is performed. Secondly, features robust to speckle noise of SAR image are detected by improving the original phase congruency based method. Then, feature descriptors are constructed on the Gaussian-Gamma-shaped edge strength map according to the histogram of oriented gradient pattern. Finally, descriptor similarity and geometrical relationship are combined to constrain the matching processing.The experimental results demonstrate that the proposed method provides significant improvement in correct matches number and image registration accuracy compared with other traditional methods.