Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot

Arnau Ramisa; David Aldavert; Shrihari Vasudevan; Ricardo Toledo; Ramon Lopez de Mantaras

doi:10.1016/B978-0-12-800881-2.00015-3

Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot

Arnau Ramisa, David Aldavert, Shrihari Vasudevan, Ricardo Toledo, Ramon Lopez de Mantaras

Department of Computer Science

Research output: Chapter in Book › Chapter › Research › peer-review

Abstract

© 2015 Zhejiang University Press Co., Ltd. Published by Elsevier Inc. All rights reserved. This chapter addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key capability in order to make robots suitable to perform complex tasks in home environments. However, finding a solution for this task is daunting: it requires the ability to handle the variability in image formation in a moving camera with tight time constraints. The chapter brings to attention some of the issues with applying three state of the art object recognition and detection methods in a mobile robotics scenario, and proposes methods to deal with windowing/segmentation. Thus, this work aims at evaluating the state-of-the-art in object perception in an attempt to develop a lightweight solution for mobile robotics use/research in typical indoor settings.

Original language	English
Title of host publication	Household Service Robotics
Pages	303-337
Number of pages	34
DOIs	https://doi.org/10.1016/B978-0-12-800881-2.00015-3
Publication status	Published - 1 Jan 2015

Keywords

Mobile robots
Object recognition

Access to Document

10.1016/B978-0-12-800881-2.00015-3

Fingerprint Dive into the research topics of 'Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot'. Together they form a unique fingerprint.

Cite this

@inbook{fa3a55dd298a4e6f939d509fb0ab6974,

title = "Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot",

abstract = "{\textcopyright} 2015 Zhejiang University Press Co., Ltd. Published by Elsevier Inc. All rights reserved. This chapter addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key capability in order to make robots suitable to perform complex tasks in home environments. However, finding a solution for this task is daunting: it requires the ability to handle the variability in image formation in a moving camera with tight time constraints. The chapter brings to attention some of the issues with applying three state of the art object recognition and detection methods in a mobile robotics scenario, and proposes methods to deal with windowing/segmentation. Thus, this work aims at evaluating the state-of-the-art in object perception in an attempt to develop a lightweight solution for mobile robotics use/research in typical indoor settings.",

keywords = "Mobile robots, Object recognition",

author = "Arnau Ramisa and David Aldavert and Shrihari Vasudevan and Ricardo Toledo and {Lopez de Mantaras}, Ramon",

year = "2015",

month = jan,

day = "1",

doi = "10.1016/B978-0-12-800881-2.00015-3",

language = "English",

isbn = "9780128009437",

pages = "303--337",

booktitle = "Household Service Robotics",

}

TY - CHAP

T1 - Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot

AU - Ramisa, Arnau

AU - Aldavert, David

AU - Vasudevan, Shrihari

AU - Toledo, Ricardo

AU - Lopez de Mantaras, Ramon

PY - 2015/1/1

Y1 - 2015/1/1

N2 - © 2015 Zhejiang University Press Co., Ltd. Published by Elsevier Inc. All rights reserved. This chapter addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key capability in order to make robots suitable to perform complex tasks in home environments. However, finding a solution for this task is daunting: it requires the ability to handle the variability in image formation in a moving camera with tight time constraints. The chapter brings to attention some of the issues with applying three state of the art object recognition and detection methods in a mobile robotics scenario, and proposes methods to deal with windowing/segmentation. Thus, this work aims at evaluating the state-of-the-art in object perception in an attempt to develop a lightweight solution for mobile robotics use/research in typical indoor settings.

AB - © 2015 Zhejiang University Press Co., Ltd. Published by Elsevier Inc. All rights reserved. This chapter addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key capability in order to make robots suitable to perform complex tasks in home environments. However, finding a solution for this task is daunting: it requires the ability to handle the variability in image formation in a moving camera with tight time constraints. The chapter brings to attention some of the issues with applying three state of the art object recognition and detection methods in a mobile robotics scenario, and proposes methods to deal with windowing/segmentation. Thus, this work aims at evaluating the state-of-the-art in object perception in an attempt to develop a lightweight solution for mobile robotics use/research in typical indoor settings.

KW - Mobile robots

KW - Object recognition

U2 - 10.1016/B978-0-12-800881-2.00015-3

DO - 10.1016/B978-0-12-800881-2.00015-3

M3 - Chapter

SN - 9780128009437

SN - 9780128008812

SP - 303

EP - 337

BT - Household Service Robotics

ER -