A Novel Two¨Cstep Strategy for Automatic GIS-Image Registration (TA-P8)

Author(s) : Zhanwu Yu (National Laboratory of Pattern Recognition,IOA,CAS, China) Veronique Prinet (National Laboratory of Pattern Recongition,IOA,CAS, China) Chunhong Pan (National Laboratory of Pattern Recongition,IOA,CAS, China)

Abstract : In this paper, we propose an automatic registration method between GIS data and high-resolution satellite images of urban scenes. Our approach consists of two steps: firstly, the urban straight main road features in images are automatically extracted by combining their spectral information with a geometric constraint. Then, by exploiting the frequency spectrum property of linear stripe regions, we attempt to match the road layer of GIS data and feature images using a new FFT-based matching algorithm. The significant advantage of the algorithm is its capability to match the rotated and scaled images robustly even when they have a large scale change or obvious geometric differences. Experimental results will demonstrate the robustness and efficiency of the method

Menu