Method and apparatus for three-dimensional, textured models from plural video images

作者: Ali Azarbayejani , Tinsley Galyean , Alex Pentland

DOI:

关键词: Tracking (particle physics)Series (mathematics)Computer visionFocal lengthArtificial intelligenceTranslation (geometry)Rotation (mathematics)Object (computer science)GeographyReference frameSegmentation

摘要: A method and apparatus for generating three-dimensional, textured computer models from a series of video images an object is disclosed. The invention operates by tracking selected group features through image frames and, based on changes in their relative positions, estimates parameters specifying camera focal length, translation rotation, the positions tracked reference frame. After segmentation into two-dimensional bounded regions that each correspond to discrete surface component actual object, texture contained various applied these produce final three-dimensional model both geometrically photometrically specified.

参考文章(28)
Shigeo Sumino, Satoshi Yoshizawa, Hirotada Ueda, Takafumi Miyatake, Method of synthesizing real image and computer graphic in image processing system ,(1992)
William A. Hanson, Wire-mesh generation from image data ,(1990)
Samuel Lee, David L. Sherman, Video system with parallel attribute interpolations ,(1991)
S. Soatto, P. Perona, R. Frezza, G. Picci, Recursive motion and structure estimation with complete error characterization computer vision and pattern recognition. pp. 428- 433 ,(1993) , 10.1109/CVPR.1993.341095
H. C. Longuet-Higgins, A computer algorithm for reconstructing a scene from two projections Nature. ,vol. 293, pp. 61- 62 ,(1987) , 10.1038/293133A0
R. Szeliski, S.B. Kang, Recovering 3D shape and motion from image streams using nonlinear least squares computer vision and pattern recognition. pp. 752- 753 ,(1993) , 10.1109/CVPR.1993.341157
Makoto Nohmi, Shinichiro Miyaoka, Makoto Kato, Texture mapping method ,(1993)