Overall view regarding fundamental matrix estimation

被引:141
作者
Armangué, X [1 ]
Salvi, J [1 ]
机构
[1] Univ Girona, Inst Informat & Applicat, Comp Vis & Robot Grp, E-17071 Girona, Spain
关键词
epipolar geometry; fundamental matrix; performance evaluation; CAMERA CALIBRATION; ACCURACY EVALUATION; EPIPOLAR GEOMETRY; ROBUST ESTIMATOR; UNCERTAINTY; MOTION; VISION;
D O I
10.1016/S0262-8856(02)00154-3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Epipolar geometry is a key point in computer vision and the fundamental matrix estimation is the only way to compute it. This article is a fresh look in the subject that overview classic and latest presented methods of fundamental matrix estimation which have been classified into linear methods, iterative methods and robust methods. All of these methods have been programmed and their accuracy analyzed in synthetic and real images. A summary including experimental results and algorithmic details is given and the whole code is available in Internet. (C) 2003 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:205 / 220
页数:16
相关论文
共 46 条
[1]   Recent progress in coded structured light as a technique to solve the correspondence problem: A survey [J].
Batlle, J ;
Mouaddib, E ;
Salvi, J .
PATTERN RECOGNITION, 1998, 31 (07) :963-982
[2]   On accurate and robust estimation of fundamental matrix [J].
Bober, M ;
Georgis, N ;
Kittler, J .
COMPUTER VISION AND IMAGE UNDERSTANDING, 1998, 72 (01) :39-53
[3]  
BROOKS MJ, 2000, P 8 IEEE INT C COMP, V1, P302
[4]  
BROOKS MJ, 1996, 4 EUR C COMP VIS CAM, V2, P415
[5]  
Chojnacki W, 2000, IEEE T PATTERN ANAL, V22, P1294, DOI 10.1109/34.888714
[6]  
CHOJNACKI W, 2002, VID PROC WORKSH ECCV
[7]   Characterizing the uncertainty of the fundamental matrix [J].
Csurka, G ;
Zeller, C ;
Zhang, ZY ;
Faugeras, OD .
COMPUTER VISION AND IMAGE UNDERSTANDING, 1997, 68 (01) :18-36
[8]  
Deriche R, 1994, LECT NOTES COMPUTER, V800, P567
[9]  
Faugeras O, 1992, EUR C COMP VIS, P321
[10]  
Faugeras O., 1993, 3 DIMENSIONAL COMPUT