A robust and hierarchical approach for the automatic co-registration of intensity and visible images

This paper presents a new robust approach to integrate intensity and visible images which have been acquired with a terrestrial laser scanner and a calibrated digital camera, respectively. In particular, an automatic and hierarchical method for the co-registration of both sensors is developed. The approach integrates several existing solutions to improve the performance of the co-registration between range-based and visible images: the Affine Scale-Invariant Feature Transform (A-SIFT), the epipolar geometry, the collinearity equations, the Groebner basis solution and the RANdom SAmple Consensus (RANSAC), integrating a voting scheme. The approach presented herein improves the existing co-registration approaches in automation, robustness, reliability and accuracy.

► Groebner basis spatial resection and RANSAC for robust and hierarchical camera resection. ► Integration of A-SIFT matching and epipolar geometry for radiometric differences. ► Fusion of intensity terrestrial laser scanner and digital camera. ► Combination of computer vision, geodesy and photogrammetry.