Title :
Regularization-based 3D object modeling from multiple range images
Author :
Hara, Kenji ; Zha, Hongbin ; Hasegawa, Tsutomu
Author_Institution :
Dept. of Electron. Technol., Fukuoka Ind. Technol. Center, Kitakyushu, Japan
Abstract :
Several methods have been proposed for building 3D object models from multiple range images mainly on the basis of the deformable models and pseudo-dynamics. However, the patches are usually placed crossing over the edge regions, and the surface orientation discontinuities cannot be properly preserved as a result. This paper proposes a new 3D object modeling method that generates refined triangular meshes while preserving the surface discontinuities. We formulate the process into a problem of minimizing an energy functional by using the idea of line processes and Markov random fields. Moreover, we show that near-optimal solutions can be obtained by utilizing the continuation method
Keywords :
Markov processes; computer vision; iterative methods; mesh generation; optimisation; solid modelling; stereo image processing; 3D object models; Markov random fields; deformable models; energy functional; iterative methods; multiple range images; optimisation; surface discontinuity; triangular meshes; Deformable models; Markov random fields;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.711848