Title :
Two-view structure-from-motion algorithm
Author :
Haoyin Zhou ; Tao Zhang
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
Structure from motion (SfM) is an important task in computer vision. Two-view SfM, which means SfM from a pair of images, is the foundation of incremental SfM methods and is quite useful in some real applications. Based on the analysis of camera geometry, this paper proposes a two-view SfM algorithm. The proposed algorithm is able to use the rotation information naturally. Simulation and experimental results show that the proposed two-view algorithm is feasible.
Keywords :
computational geometry; computer vision; image sensors; iterative methods; motion estimation; 3D scene structure estimation; camera geometry analysis; camera motion estimation; computer vision; iterative method; two-view SfM algorithm; two-view structure-from-motion algorithm; Algorithm design and analysis; Cameras; Computer vision; Convergence; Geometry; Silicon; Three-dimensional displays; iterative method; two-view SfM;
Conference_Titel :
Intelligent Control and Automation (WCICA), 2014 11th World Congress on
DOI :
10.1109/WCICA.2014.7053269
