Object-based place recognition for mobile robots using panoramas

Arturo Ribes; Arnau Ramisa; Ramon Lopez de Mantaras; Ricardo Toledo

doi:10.3233/978-1-58603-925-7-388

Object-based place recognition for mobile robots using panoramas

Arturo Ribes
, Arnau Ramisa
, Ramon Lopez de Mantaras
, Ricardo Toledo

Research output: Chapter in Book / Conference Paper › Chapter

1 Citation (Scopus)

Abstract

Object recognition has been widely researched for several decades and in the recent years new methods capable of general object classification have appeared. However very few work has been done to adapt these methods to the challenges raised by mobile robotics. In this article we discuss the data sources (appearence information, temporal context, etc.) that such methods could use and we review several state of the art object recognition methods that build in one or more of these sources. Finally we run an object based robot localization experiment using an state of the art object recognition method and we show that good results are obtained even with a naÃ¯ve place descriptor.

Original language	English
Title of host publication	Artificial Intelligence Research and Development
Editors	Teresa Alsinet, Josep Puyol-Gruart, Carme Torras
Place of Publication	The Netherlands
Publisher	IOS Press
Pages	388-397
Number of pages	10
ISBN (Electronic)	9781607503750
ISBN (Print)	9781586039257
DOIs	https://doi.org/10.3233/978-1-58603-925-7-388
Publication status	Published - 2008

Access to Document

10.3233/978-1-58603-925-7-388

Cite this

@inbook{9eb6568f58614037822a15bb4a87a64a,

title = "Object-based place recognition for mobile robots using panoramas",

abstract = "Object recognition has been widely researched for several decades and in the recent years new methods capable of general object classification have appeared. However very few work has been done to adapt these methods to the challenges raised by mobile robotics. In this article we discuss the data sources (appearence information, temporal context, etc.) that such methods could use and we review several state of the art object recognition methods that build in one or more of these sources. Finally we run an object based robot localization experiment using an state of the art object recognition method and we show that good results are obtained even with a na{\~A}¯ve place descriptor.",

author = "Arturo Ribes and Arnau Ramisa and \{Lopez de Mantaras\}, Ramon and Ricardo Toledo",

year = "2008",

doi = "10.3233/978-1-58603-925-7-388",

language = "English",

isbn = "9781586039257",

pages = "388--397",

editor = "Teresa Alsinet and Josep Puyol-Gruart and Carme Torras",

booktitle = "Artificial Intelligence Research and Development",

publisher = "IOS Press",

}

TY - CHAP

T1 - Object-based place recognition for mobile robots using panoramas

AU - Ribes, Arturo

AU - Ramisa, Arnau

AU - Lopez de Mantaras, Ramon

AU - Toledo, Ricardo

PY - 2008

Y1 - 2008

N2 - Object recognition has been widely researched for several decades and in the recent years new methods capable of general object classification have appeared. However very few work has been done to adapt these methods to the challenges raised by mobile robotics. In this article we discuss the data sources (appearence information, temporal context, etc.) that such methods could use and we review several state of the art object recognition methods that build in one or more of these sources. Finally we run an object based robot localization experiment using an state of the art object recognition method and we show that good results are obtained even with a naÃ¯ve place descriptor.

AB - Object recognition has been widely researched for several decades and in the recent years new methods capable of general object classification have appeared. However very few work has been done to adapt these methods to the challenges raised by mobile robotics. In this article we discuss the data sources (appearence information, temporal context, etc.) that such methods could use and we review several state of the art object recognition methods that build in one or more of these sources. Finally we run an object based robot localization experiment using an state of the art object recognition method and we show that good results are obtained even with a naÃ¯ve place descriptor.

UR - http://handle.uws.edu.au:8081/1959.7/531459

U2 - 10.3233/978-1-58603-925-7-388

DO - 10.3233/978-1-58603-925-7-388

M3 - Chapter

SN - 9781586039257

SP - 388

EP - 397

BT - Artificial Intelligence Research and Development

A2 - Alsinet, Teresa

A2 - Puyol-Gruart, Josep

A2 - Torras, Carme

PB - IOS Press

CY - The Netherlands

ER -

Object-based place recognition for mobile robots using panoramas

Abstract

Access to Document

Other files and links

Fingerprint

Cite this