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

详细信息	查看全文 | 推荐本文 |

• 作者：Diego Gonz&#225 ; lez-Aguilera^a ; ^{daguilera@usal.es} ; Pablo Rodrí ; guez-Gonz&#225 ; lvez^a ; David Hern&#225 ; ndez-Ló ; pez^b ; ^{david.hernandez@uclm.es} ; José ; Luis Lerma^c ; ^{jllerma@cgf.upv.es}
• 关键词：Groebner basis ; Close-range photogrammetry ; Sensor registration
• 刊名：Optics and Laser Technology
• 出版年：2012
• 期刊代码：48_00303992
• 类别：ph
• 出版时间：September, 2012
• 卷：44
• 期：6
• 页码：1915-1923
• 文件大小：709 K

摘要

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.