An image matching algorithm combining local and semi-global geometry preservation
Remote sensing image matching is an essential preprocessing step for many remote sensing applications.However,the distortions caused by elevation differences and the complexity of remote sensing image matching severely limit the matching precision of high-resolution remote sensing images.This paper proposes a robust feature matching algorithm suitable for local distortion and high outlier ratio.First,the Delaunay triangulation algorithm is used to impose geometric constraints on the initial matching point set,and the local adjacency relationship of the feature points is obtained.Second,pre-filter is conducted based on the adjacency information.Third,a multi-scale strategy is used to establish the local adjacency consistent model.Finally,a triangle similarity function is defined to achieve matching recovery.The experimental results on high-resolution images show that the average accuracy of our algorithm is 7.69％higher than that of RANSAC,and it is still robust when the outlier ratio is higher than 90％.
high resolution remote sensing imageimage matchingDelaunay triangulationgeometry preservationmulti-scale
国家科技期刊平台
NSTL
万方数据
维普
