This paper proposes a new registration algorithm for synthetic aperture radar (SAR) images and visible light images using nonlinear diffusion equations and Hausdorff measure. In this algorithm, the SAR image segmentation algorithm based on nonlinear diffusion equations is first used to obtain the corresponding closed area features in the SAR image and the optical binary image. After the centroid coordinates of the closed area are overlapped, the extracted features can be used to quickly and roughly match the images through Hausdorff measure and genetic algorithm. Based on the rough registration, the correlation of the binary images is finally used for fine registration. Experimental results show that the proposed method has good robustness and high registration accuracy, and can automatically complete the registration of images to be matched with large coordinate translation, angle transformation, and scale scaling.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore