Title :
A method for 3D surface reconstruction from range images
Author :
Shiwei, Deng ; Baozong, Yuan
Author_Institution :
Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
Abstract :
A method for 3D surface reconstruction from range images is proposed. It uses the implicit algebraic shape primitive which allows for a host of possible shapes. First by using the segmentation method based on mathematical morphology, the range image is segmented into regions corresponding to the surface patches on objects. Then the algebraic surfaces are fitted to the range points in these regions by solving a generalized eigenvector problem. It is proved that this scheme is viewpoint invariant and computationally efficient, and in comparison with other implicit surface reconstruction techniques, can represent more general 3D surfaces
Keywords :
computational complexity; computer vision; eigenvalues and eigenfunctions; image reconstruction; image segmentation; mathematical morphology; 3D surface reconstruction; algebraic shape primitive; algebraic surfaces; computational efficiency; generalized eigenvector problem; mathematical morphology; range images; segmentation method; surface patches; Image reconstruction; Image segmentation; Information science; Machine vision; Polynomials; Shape; Surface fitting; Surface morphology; Surface reconstruction; Vectors;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344878
