Extraction, matching, and pose recovery based on dominant rectangular structures

被引：64

作者：

Kosecká, J ^{[1
]}

Zhang, W ^{[1
]}

机构：

[1] George Mason Univ, Dept Comp Sci, Fairfax, VA 22030 USA

来源：

COMPUTER VISION AND IMAGE UNDERSTANDING | 2005年 / 100卷 / 03期

关键词：

model-based reconstruction; pose recovery; wide-baseline matching;

D O I：

10.1016/j.cviu.2005.04.005

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Man-made environments possess many regularities which can be efficiently exploited for image-based rendering as well as robotic navigation and localization tasks. In this paper, we present an approach for automatic extraction of dominant rectangular structures from a single view and show how they facilitate the recovery of camera pose, planar structure, and matching across widely separated views. In the presented approach, the rectangular hypothesis formation is based on a higher-level information encoded by the presence of orthogonal vanishing directions, the dominant rectangular structures can be detected and matched despite the presence of multiple repetitive structures often encountered in a variety of buildings. Different stages of the approach are demonstrated on various examples of images of indoor and outdoor structured environments. (c) 2005 Elsevier Inc. All rights reserved.

引用

页码：274 / 293

页数：20

共 21 条

[1]

ANTONE M, 2000, IEEE P CVPR

[2] NEW METHOD FOR VANISHING POINT DETECTION [J].

BRILLAULTOMAHONY, B .

CVGIP-IMAGE UNDERSTANDING, 1991, 54 (02) :289-300

[3]

CIPOLLA R, 1999, P IEEE INT C MULT CO

[4]

Collins R. T., 1990, Proceedings. Third International Conference on Computer Vision (Cat. No.90CH2934-8), P400, DOI 10.1109/ICCV.1990.139560

[5] Single view metrology [J].

Criminisi, A ;

Reid, I ;

Zisserman, A .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2000, 40 (02) :123-148

[6]

Debevec P. E., 1996, Computer Graphics Proceedings. SIGGRAPH '96, P11, DOI 10.1145/237170.237191

[7]

Dick AR, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P268, DOI 10.1109/ICCV.2001.937528

[8] Reconstruction of linearly parameterized models from single images with a camera of unknown focal length [J].

Jelinek, D ;

Taylor, CJ .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (07) :767-773

[9]

Kosecka J., 2002, ECCV

[10]

Liebowitz D., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P293, DOI 10.1109/ICCV.1999.791233

← 1 2 3 →