کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
733806 | 893368 | 2012 | 9 صفحه PDF | دانلود رایگان |
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.
Journal: Optics & Laser Technology - Volume 44, Issue 6, September 2012, Pages 1915–1923