A general expression of the fundamental matrix for both perspective and affine cameras
被引:0
作者:
Zhang, ZY
论文数: 0引用数: 0
h-index: 0
机构:
ATR, Human Informat Proc Res Lab, Kyoto 61902, JapanATR, Human Informat Proc Res Lab, Kyoto 61902, Japan
Zhang, ZY
[1
]
Xu, G
论文数: 0引用数: 0
h-index: 0
机构:
ATR, Human Informat Proc Res Lab, Kyoto 61902, JapanATR, Human Informat Proc Res Lab, Kyoto 61902, Japan
Xu, G
[1
]
机构:
[1] ATR, Human Informat Proc Res Lab, Kyoto 61902, Japan
来源:
IJCAI-97 - PROCEEDINGS OF THE FIFTEENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 AND 2
|
1997年
关键词:
motion analysis;
epipolar geometry;
uncalibrated images;
non-metric vision;
3D reconstruction;
fundamental matrix;
D O I:
暂无
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
This paper addresses the recovery of structure and motion from two uncalibrated images of a scene under full perspective or under affine projection. Epipolar geometry, projective reconstruction, and affine reconstruction are elaborated in a way such that everyone having knowledge of linear algebra can understand the discussion without difficultly. A general expression of the fundamental matrix is derived which is valid for ang: projection model without lens distortion (including full perspective and affine camera). A new technique for affine reconstruction from tw uro affine images is developed, which consists in first estimating the affine epipolar geometry and then performing a triangulation for each point match with respect to an implicit common affine basis. This technique is very efficient.