Affine structure from line correspondences with uncalibrated affine cameras

被引：71

作者：

Quan, L ^{[1
]}

Kanade, T ^{[1
]}

机构：

[1] CARNEGIE MELLON UNIV, INST ROBOT, PITTSBURGH, PA 15213 USA

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1997年 / 19卷 / 08期

关键词：

structure from motion; affine structure; factorization method; line correspondence; affine camera; one-dimensional camera; uncalibrated image;

D O I：

10.1109/34.608285

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 presents a linear algorithm for recovering 3D affine shape and motion from line correspondences with uncalibrated affine cameras. The algorithm requires a minimum of seven line correspondences over three views. The key idea is the introduction of a one-dimensional projective camera. This converts 3D affine reconstruction of ''line directions'' into 2D projective reconstruction of ''points.'' In addition, a line-based factorization method is also proposed to handle redundant views. Experimental results both on simulated and real image sequences validate the robustness and the accuracy of the algorithm.

引用

页码：834 / 845

页数：12

共 46 条

[1] PERSPECTIVE APPROXIMATIONS
ALOIMONOS, JY
[J]. IMAGE AND VISION COMPUTING, 1990, 8 (03) : 179 - 192
[2] AYACHE N, 1990, STEREOVISION SENSOR
[3] BEARDSLEY PA, 1995, FIFTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, PROCEEDINGS, P58, DOI 10.1109/ICCV.1995.466806
[4] CARLSSON S, IN PRESS INT J COMP
[5] DETERMINATION OF THE ATTITUDE OF 3-D OBJECTS FROM A SINGLE PERSPECTIVE VIEW
DHOME, M
RICHETIN, M
LAPRESTE, JT
RIVES, G
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (12) : 1265 - 1278
[6] FAUGERAS O, 1995, FIFTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, PROCEEDINGS, P951, DOI 10.1109/ICCV.1995.466832
[7] FAUGERAS OD, 1992, LECT NOTES COMPUT SC, V588, P564
[8] FAUGERAS OD, 1987, P 1 INT C COMP VIS L
[9] Golub G, 2013, Matrix Computations, V4th
[10] Hartley R., 1992, Proceedings. 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.92CH3168-2), P761, DOI 10.1109/CVPR.1992.223179

← 1 2 3 4 5 →