Epipolar geometry estimation via RANSAC benefits from the oriented epipolar constraint

被引：33

作者：

Chum, O ^{[1
]}

Werner, T ^{[1
]}

Matas, J ^{[1
]}

机构：

[1] Czech Tech Univ, Fac Elect Engn, Dept Cybernet, Ctr Machine Percept, Prague 16627 6, Czech Republic

来源：

PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1 | 2004年

关键词：

D O I：

10.1109/ICPR.2004.1334020

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The efficiency of epipolar geometry estimation by RANSAC is improved by exploiting the oriented epipolar constraint. Performance evaluation shows that the enhancement brings up to a two-fold speed-up. The orientation test is simple to implement, is universally applicable and takes negligible fraction of time compared with epipolar geometry computation.

引用

页码：112 / 115

页数：4

共 17 条

[1]

Chum O., 2004, P ACCV, V2, P812

[2] RANDOM SAMPLE CONSENSUS - A PARADIGM FOR MODEL-FITTING WITH APPLICATIONS TO IMAGE-ANALYSIS AND AUTOMATED CARTOGRAPHY [J].

FISCHLER, MA ;

BOLLES, RC .

COMMUNICATIONS OF THE ACM, 1981, 24 (06) :381-395

[3]

Harris C., 1988, Alvey Vis. Conf., V15, P10, DOI DOI 10.5244/C.2.23

[4]

Hartley R., 2000, MULTIPLE VIEW GEOMET

[5]

LAVEAU S, 1994, INT C PATT RECOG, P689, DOI 10.1109/ICPR.1994.576404

[6]

LAVEAU S, 1996, P ECCV, V1, P149

[7]

Matas J, 2002, INT C PATT RECOG, P363, DOI 10.1109/ICPR.2002.1047471

[8]

Matas J., 2002, Electronic Proceedings of the 13th British Machine Vision Conference, P384

[9]

MIKOLAJCZYK K, 2002, P ECCV, V1, P128

[10]

Nistér D, 2003, NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, P199

← 1 2 →