Multi-cue visual obstacle detection for mobile robots

Luis Jesús Manso Fernández-Arguelles; Pablo Bustos García de Castro; Pilar Bachiller Burgos; José Moreno del Pozo

doi:10.14198/jopha.2010.4.1.02

Multi-cue visual obstacle detection for mobile robots

Luis Jesús Manso Fernández-Arguelles, Pablo Bustos García de Castro, Pilar Bachiller Burgos, José Moreno del Pozo

College of Engineering and Physical Sciences

Research output: Contribution to journal › Article › peer-review

Abstract

Autonomous navigation is one of the most essential capabilities of autonomous robots. In order to navigate autonomously, robots need to detect obstacles. While many approaches achieve good results tackling this problem with lidar sensor devices, vision based approaches are cheaper and richer solutions. This paper presents an algorithm for obstacle detection using a stereo camera pair that overcomes some of the limitations of the existing state of the art algorithms and performs better in many heterogeneous scenarios. We use both geometric and color based cues in order to improve its robustness. The contributions of the paper are improvements to the state of the art on single and multiple cue obstacle detection algorithms and a new heuristic method for merging its outputs.

Original language	English
Pages (from-to)	3-10
Journal	Journal of Physical Agents (JoPha)
Volume	4
Issue number	1
DOIs	https://doi.org/10.14198/jopha.2010.4.1.02
Publication status	Published - Jan 2010

Bibliographical note

This document is under a Creative Commons Attribution 4.0 International license (CC BY 4.0)

Access to Document

10.14198/jopha.2010.4.1.02Licence: CC BY 3.0

Multi-cue_Visual_Obstacle_Detection_for_Mobile_Robots
This document is under a Creative Commons Attribution 4.0 International license (CC BY 4.0)
Final published version, 2.35 MBLicence: CC BY 3.0

Cite this

@article{b17645c8b8dd4a249d2d621d84c9329c,

title = "Multi-cue visual obstacle detection for mobile robots",

abstract = "Autonomous navigation is one of the most essential capabilities of autonomous robots. In order to navigate autonomously, robots need to detect obstacles. While many approaches achieve good results tackling this problem with lidar sensor devices, vision based approaches are cheaper and richer solutions. This paper presents an algorithm for obstacle detection using a stereo camera pair that overcomes some of the limitations of the existing state of the art algorithms and performs better in many heterogeneous scenarios. We use both geometric and color based cues in order to improve its robustness. The contributions of the paper are improvements to the state of the art on single and multiple cue obstacle detection algorithms and a new heuristic method for merging its outputs.",

author = "Fern{\'a}ndez-Arguelles, {Luis Jes{\'u}s Manso} and Castro, {Pablo Bustos Garc{\'i}a de} and Burgos, {Pilar Bachiller} and Pozo, {Jos{\'e} Moreno del}",

note = "This document is under a Creative Commons Attribution 4.0 International license (CC BY 4.0)",

year = "2010",

month = jan,

doi = "10.14198/jopha.2010.4.1.02",

language = "English",

volume = "4",

pages = "3--10",

number = "1",

}

TY - JOUR

T1 - Multi-cue visual obstacle detection for mobile robots

AU - Fernández-Arguelles, Luis Jesús Manso

AU - Castro, Pablo Bustos García de

AU - Burgos, Pilar Bachiller

AU - Pozo, José Moreno del

N1 - This document is under a Creative Commons Attribution 4.0 International license (CC BY 4.0)

PY - 2010/1

Y1 - 2010/1

N2 - Autonomous navigation is one of the most essential capabilities of autonomous robots. In order to navigate autonomously, robots need to detect obstacles. While many approaches achieve good results tackling this problem with lidar sensor devices, vision based approaches are cheaper and richer solutions. This paper presents an algorithm for obstacle detection using a stereo camera pair that overcomes some of the limitations of the existing state of the art algorithms and performs better in many heterogeneous scenarios. We use both geometric and color based cues in order to improve its robustness. The contributions of the paper are improvements to the state of the art on single and multiple cue obstacle detection algorithms and a new heuristic method for merging its outputs.

AB - Autonomous navigation is one of the most essential capabilities of autonomous robots. In order to navigate autonomously, robots need to detect obstacles. While many approaches achieve good results tackling this problem with lidar sensor devices, vision based approaches are cheaper and richer solutions. This paper presents an algorithm for obstacle detection using a stereo camera pair that overcomes some of the limitations of the existing state of the art algorithms and performs better in many heterogeneous scenarios. We use both geometric and color based cues in order to improve its robustness. The contributions of the paper are improvements to the state of the art on single and multiple cue obstacle detection algorithms and a new heuristic method for merging its outputs.

UR - https://www.jopha.ua.es/article/view/2010-v4-n1-multi-cue-visual-obstacle-detection-for-mobile-robots

U2 - 10.14198/jopha.2010.4.1.02

DO - 10.14198/jopha.2010.4.1.02

M3 - Article

SN - 1888-0258

VL - 4

SP - 3

EP - 10

JO - Journal of Physical Agents (JoPha)

JF - Journal of Physical Agents (JoPha)

IS - 1

ER -

Multi-cue visual obstacle detection for mobile robots

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this