Affine reconstruction from perspective image pairs with a relative object-camera translation in between

被引：44

作者：

Moons, T

VanGool, L

Proesmans, M

Pauwels, E

机构：

[1] Machine Intelligence and Imaging Research Group, Department of Electrical Engineering (E.S.A.T.), Katholieke Universiteit Leuven, Kurd, B-3001 Leuven (Heverlee)

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1996年 / 18卷 / 01期

关键词：

affine reconstruction; camera translation; stereo; shape-from-motion; repeated structure; perspective projection;

D O I：

10.1109/34.476015

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A method is described to recover the three-dimensional affine structure of a scene consisting of at least five points identified in two perspective views with a relative object-camera translation in between. When compared to the results for arbitrary stereo views, a more detailed reconstruction is possible using less information. The method presented only assumes that the two images are obtained by Identical cameras, but no knowledge about the intrinsic parameters of the camera(s) or about the performed translation is assumed, By the same method, affine 3D reconstruction from a single view can be achieved for parallel structures. In that case, four points suffice for affine reconstruction.

引用

页码：77 / 83

页数：7

共 17 条

[11]

Moons T., 1994, Applications of Invariance in Computer Vision. Second Joint European - US Workshop Proceedings, P297

[12]

MOONS T, 1994, KULESATM129420 KATH

[13]

PROESMANS M, 1994, COMPUTER VISION ECCV

[14]

QUAN L, 1993, 4TH P BRIT MACH VIS, P659

[15]

ROTHWELL CA, 1993, P IEEE INT C COMPUTE, P573

[16]

Semple J.G., 1979, Algebraic Projective Geometry

[17]

SHASHUA A, 1994, 1994 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, P483, DOI 10.1109/CVPR.1994.323870

← 1 2 →