Natural, salient image patches for robot localization

被引：2

作者：

Fraundorfer, F ^{[1
]}

Bischof, H ^{[1
]}

Ober, S ^{[1
]}

机构：

[1] Graz Univ Technol, Inst Comp Graph & Vis, A-8010 Graz, Austria

来源：

PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4 | 2004年

关键词：

D O I：

10.1109/ICPR.2004.1333913

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 addresses a major problem in. mobile robot localization. In most approaches to simultaneous localization and mapping (SLAM) only line and point features are used which easily lead to ambiguities in loop-closing and global relocalization. In this work we propose to use natural, salient image patches as additional high discriminative landmarks to aid in unclear localization scenarios which might occur in modern highly symmetric indoor environments. A new method of landmark extraction is presented as well as a matching method for storing and retrieving the landmarks in a location database.

引用

页码：881 / 884

页数：4

共 7 条

[1]

[Anonymous], 1988, ALVEY VISION C

[2]

Bosse M, 2002, 2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, P513, DOI 10.1109/ICIP.2002.1039020

[3]

BOSSE M, 2003, IEEE INT C ROB AUT

[4]

Obdrzalek S., 2002, P BRIT MACH VIS C, P1

[5] Evaluation of interest point detectors [J].

Schmid, C ;

Mohr, R ;

Bauckhage, C .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2000, 37 (02) :151-172

[6]

SURMANN H, 2003, AUTONOMOUS MOBILE RO, V45, P181

[7] GRAPH-THEORETICAL METHODS FOR DETECTING AND DESCRIBING GESTALT CLUSTERS [J].

ZAHN, CT .

IEEE TRANSACTIONS ON COMPUTERS, 1971, C 20 (01) :68-&

← 1 →