A Novel Line Matching Method Based on Intersection Context

被引：21

作者：

Kim, Hyunwoo ^{[2
]}

Lee, Sukhan ^{[1
]}

机构：

[1] Sungkyunkwan Univ, Sch Informat & Commun Engn, Suwon, South Korea

[2] Korean German Inst Technol, Dept New Media, Seoul, South Korea

来源：

2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) | 2010年

关键词：

D O I：

10.1109/ROBOT.2010.5509472

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents a novel line matching method based on the intersection context of coplanar line pairs especially working in poorly textured indoor scenes. To overcome the matching ambiguity of single line segments, intersecting line pairs in 2D images are utilized for line matching. Coplanarity of the intersecting line pairs and their corresponding intersection context discriminate true intersecting line pairs from false intersecting ones in 3D world. Compared to previous approaches, the proposed method can match line segments and estimate camera geometry simultaneously not knowing camera geometry in advance or not considering topological relations of all line segments. Comparison studies and experimental results prove the accuracy and speed of the proposed method in real world situations.

引用

页码：1014 / 1021

页数：8

共 22 条

[1]

[Anonymous], 2001, Robotica, DOI DOI 10.1017/S0263574700223217

[2]

[Anonymous], 2009, PEARSON ED INDIA

[3]

Baillard C., 1999, Conference on Automatic Extraction of GIS Objects from Digital Imagery, IAPRS, V32, P69

[4]

Bartoli A, 2003, NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, P207

[5]

Bay H, 2005, PROC CVPR IEEE, P329

[6]

BAY H, 2006, 3DPVT06, P496

[7]

Gunhee Kim, 2007, Recent Progress in Robotics: Viable Robotic Service to Human. 13th International Conference on Advanced Robotics, ICAR 2007, P255

[8]

Harris C, 1988, ALVEY VISION C, V15, P10, DOI DOI 10.5244/C.2.23

[9]

Kim E., 2008, RO MAN07 JEJ ISL KOR, P516

[10]

Lloyd B., 2003, COMPUTATION FUNDAMEN

← 1 2 3 →