Large scale visual odometry using stereo vision

Andres Hernandez-Gutierrez, Juan I. Nieto, Teresa Vidal-Calleja, Eduardo Nebot

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper presents a system for egomotion estimation using a stereo head camera. The camera motion estimation is based on features tracked along a video sequence. The system also estimates the tridimensional geometry of the environment by fusing the visual information from multiple views. Furthermore, the paper presents comparisons between two different algorithms. The first one is by applying triangulation to 3D points. Motion estimation using 3D points suffers from the problem of nonisotropic noise due to the large uncertainty in depth estimation. To deal with this problem we present results with a second approach that works directly in the disparity space. Experimental results using a mobile platform are presented. The experiments cover long distances in urban-like environments with the presence of dynamic objects. The system presented is part of a bigger project involving autonomous navigation using vision only.

Original languageEnglish
Title of host publicationProceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009
Publication statusPublished - 1 Dec 2009
Event2009 Australasian Conference on Robotics and Automation, ACRA 2009 - Sydney, NSW, Australia
Duration: 2 Dec 20094 Dec 2009

Publication series

NameProceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009

Conference

Conference2009 Australasian Conference on Robotics and Automation, ACRA 2009
CountryAustralia
CitySydney, NSW
Period2/12/094/12/09

Fingerprint

Stereo vision
Motion estimation
Cameras
Triangulation
Navigation
Geometry
Experiments
Uncertainty

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Hernandez-Gutierrez, A., Nieto, J. I., Vidal-Calleja, T., & Nebot, E. (2009). Large scale visual odometry using stereo vision. In Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009 (Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009).
Hernandez-Gutierrez, Andres ; Nieto, Juan I. ; Vidal-Calleja, Teresa ; Nebot, Eduardo. / Large scale visual odometry using stereo vision. Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009. 2009. (Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009).
@inproceedings{1b3dfab2dfbb4954b4819d1c3cbf4247,
title = "Large scale visual odometry using stereo vision",
abstract = "This paper presents a system for egomotion estimation using a stereo head camera. The camera motion estimation is based on features tracked along a video sequence. The system also estimates the tridimensional geometry of the environment by fusing the visual information from multiple views. Furthermore, the paper presents comparisons between two different algorithms. The first one is by applying triangulation to 3D points. Motion estimation using 3D points suffers from the problem of nonisotropic noise due to the large uncertainty in depth estimation. To deal with this problem we present results with a second approach that works directly in the disparity space. Experimental results using a mobile platform are presented. The experiments cover long distances in urban-like environments with the presence of dynamic objects. The system presented is part of a bigger project involving autonomous navigation using vision only.",
author = "Andres Hernandez-Gutierrez and Nieto, {Juan I.} and Teresa Vidal-Calleja and Eduardo Nebot",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9780980740400",
series = "Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009",
booktitle = "Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009",

}

Hernandez-Gutierrez, A, Nieto, JI, Vidal-Calleja, T & Nebot, E 2009, Large scale visual odometry using stereo vision. in Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009. Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009, 2009 Australasian Conference on Robotics and Automation, ACRA 2009, Sydney, NSW, Australia, 2/12/09.

Large scale visual odometry using stereo vision. / Hernandez-Gutierrez, Andres; Nieto, Juan I.; Vidal-Calleja, Teresa; Nebot, Eduardo.

Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009. 2009. (Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Large scale visual odometry using stereo vision

AU - Hernandez-Gutierrez, Andres

AU - Nieto, Juan I.

AU - Vidal-Calleja, Teresa

AU - Nebot, Eduardo

PY - 2009/12/1

Y1 - 2009/12/1

N2 - This paper presents a system for egomotion estimation using a stereo head camera. The camera motion estimation is based on features tracked along a video sequence. The system also estimates the tridimensional geometry of the environment by fusing the visual information from multiple views. Furthermore, the paper presents comparisons between two different algorithms. The first one is by applying triangulation to 3D points. Motion estimation using 3D points suffers from the problem of nonisotropic noise due to the large uncertainty in depth estimation. To deal with this problem we present results with a second approach that works directly in the disparity space. Experimental results using a mobile platform are presented. The experiments cover long distances in urban-like environments with the presence of dynamic objects. The system presented is part of a bigger project involving autonomous navigation using vision only.

AB - This paper presents a system for egomotion estimation using a stereo head camera. The camera motion estimation is based on features tracked along a video sequence. The system also estimates the tridimensional geometry of the environment by fusing the visual information from multiple views. Furthermore, the paper presents comparisons between two different algorithms. The first one is by applying triangulation to 3D points. Motion estimation using 3D points suffers from the problem of nonisotropic noise due to the large uncertainty in depth estimation. To deal with this problem we present results with a second approach that works directly in the disparity space. Experimental results using a mobile platform are presented. The experiments cover long distances in urban-like environments with the presence of dynamic objects. The system presented is part of a bigger project involving autonomous navigation using vision only.

UR - http://www.scopus.com/inward/record.url?scp=84855571792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855571792&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84855571792

SN - 9780980740400

T3 - Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009

BT - Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009

ER -

Hernandez-Gutierrez A, Nieto JI, Vidal-Calleja T, Nebot E. Large scale visual odometry using stereo vision. In Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009. 2009. (Proceedings of the 2009 Australasian Conference on Robotics and Automation, ACRA 2009).