Registration and integration algorithm in structured light three-dimensional scanning based on scale-invariant feature matching of multi-source images
Registration and integration algorithm in structured light three-dimensional scanning based on scale-invariant feature matching of multi-source images作者机构:Key Laboratory of Digital Medical Equipment TechnologyNanjing University of Aeronautic and Astronautic
出 版 物:《Chinese Optics Letters》 (中国光学快报(英文版))
年 卷 期:2012年第10卷第9期
页 面:25-29页
核心收录:
学科分类:08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程]
基 金:supported by the National "863" Program of China (No. 2009BAI81B02) the Doctoral Foundation of the Ministry of Education (No.20070287055)
主 题:Algorithms Computerized tomography Image matching Three dimensional computer graphics
摘 要:Based on the homography between a multi-source image and three-dimensional (3D) measurement points, this letter proposes a novel 3D registration and integration method based on scale-invariant feature matching. The matching relationships of two-dimensional (2D) texture gray images and two-and-a-half- dimensional (2.5D) range images are constructed using the scale-invariant feature transform algorithms. Then, at least three non-collinear 3D measurement points corresponding to image feature points are used to achieve a registration relationship accurately. According to the index of overlapping images and the local 3D border search method, multi-view registration data are rapidly and accurately integrated. Exper- imental results on real models demonstrate that the algorithm is robust and effective.