Title :
Three-dimensional curve reconstruction from multiple images
Author :
Mai, Fei ; Hung, Y.S.
Author_Institution :
Dept. of Electr. & Electron. Eng., Univ. of Hong Kong, Hong Kong, China
fDate :
7/1/2012 12:00:00 AM
Abstract :
In this study, the authors propose a new approach for reconstructing three-dimensional (3D) curves from multiple 2D images taken by uncalibrated cameras. The method is point based and does not require parameterisation of 2D or 3D curves. 2D curves are detected on multiple views as sequences of sampled points along the curves. A curve in 3D space is reconstructed as a sequence of 3D points sampled along the curve that minimise the geometric distances from their projections to the measured 2D curves on different images (i.e. 2D reprojection error). The minimisation problem is solved by an iterative algorithm which is guaranteed to converge to a (local) minimum of the 2D reprojection error. Without requiring calibrated cameras or additional point features, their method can reconstruct multiple 3D curves simultaneously from multiple images and it readily handles images with missing and/or partially occluded curves.
Keywords :
cameras; computational geometry; curve fitting; image reconstruction; image sequences; iterative methods; minimisation; 2D curve detection; 2D reprojection error; 3D points sequence; 3D space; geometric distance minimisation; iterative algorithm; minimisation problem; missing curves; multiple 2D images; multiple 3D curve reconstruction; partially occluded curves; sampled points sequences; three-dimensional curve reconstruction; uncalibrated cameras;
Journal_Title :
Computer Vision, IET
DOI :
10.1049/iet-cvi.2011.0085