Three-dimensional mapping utilizing stereo vision and Bayesian inference

Tatsunori Kou; Kenji Suzuki; Shuji Hashimoto

doi:10.1117/12.580585

Three-dimensional mapping utilizing stereo vision and Bayesian inference

Tatsunori Kou^*, Kenji Suzuki, Shuji Hashimoto

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

In this study we propose a method for creating 3D map of real world environment by using 3D occupancy grids. The map is created by characterizing each grid associated with a certain area in the real world environment by utilizing multiple measurements using stereo vision and Bayesian inference. The proposed method can absorb the measurement uncertainties caused in the stereo matching process and in the system's calibrations. The preliminary experiments show that the proposed algorithm is able to robustly generate environment maps. The algorithm is also suitable to be implemented as a vision system for autonomous mobile robots.

Original language	English
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Editors	S. Kaneko, H. Cho, G.K. Knopf, R. Tutsch
Pages	111-118
Number of pages	8
Volume	5603
DOIs	https://doi.org/10.1117/12.580585
Publication status	Published - 2004
Event	Machine Vision and its Optomechatronic Applications - Philadelphia, PA, United States Duration: 2004 Oct 26 → 2004 Oct 28

Other

Other	Machine Vision and its Optomechatronic Applications
Country/Territory	United States
City	Philadelphia, PA
Period	04/10/26 → 04/10/28

Keywords

Bayesian inference
Mapping
Mobile robots
Occupancy grids
Stereo vision

ASJC Scopus subject areas

Electrical and Electronic Engineering
Condensed Matter Physics

Access to Document

10.1117/12.580585

Cite this

Kou, T, Suzuki, K & Hashimoto, S 2004, Three-dimensional mapping utilizing stereo vision and Bayesian inference. in S Kaneko, H Cho, GK Knopf & R Tutsch (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5603, 15, pp. 111-118, Machine Vision and its Optomechatronic Applications, Philadelphia, PA, United States, 04/10/26. https://doi.org/10.1117/12.580585

@inproceedings{4aeb2d0eb19d47db9acb560de2dd22af,

title = "Three-dimensional mapping utilizing stereo vision and Bayesian inference",

abstract = "In this study we propose a method for creating 3D map of real world environment by using 3D occupancy grids. The map is created by characterizing each grid associated with a certain area in the real world environment by utilizing multiple measurements using stereo vision and Bayesian inference. The proposed method can absorb the measurement uncertainties caused in the stereo matching process and in the system's calibrations. The preliminary experiments show that the proposed algorithm is able to robustly generate environment maps. The algorithm is also suitable to be implemented as a vision system for autonomous mobile robots.",

keywords = "Bayesian inference, Mapping, Mobile robots, Occupancy grids, Stereo vision",

author = "Tatsunori Kou and Kenji Suzuki and Shuji Hashimoto",

year = "2004",

doi = "10.1117/12.580585",

language = "English",

volume = "5603",

pages = "111--118",

editor = "S. Kaneko and H. Cho and G.K. Knopf and R. Tutsch",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

note = "Machine Vision and its Optomechatronic Applications ; Conference date: 26-10-2004 Through 28-10-2004",

}

TY - GEN

T1 - Three-dimensional mapping utilizing stereo vision and Bayesian inference

AU - Kou, Tatsunori

AU - Suzuki, Kenji

AU - Hashimoto, Shuji

PY - 2004

Y1 - 2004

N2 - In this study we propose a method for creating 3D map of real world environment by using 3D occupancy grids. The map is created by characterizing each grid associated with a certain area in the real world environment by utilizing multiple measurements using stereo vision and Bayesian inference. The proposed method can absorb the measurement uncertainties caused in the stereo matching process and in the system's calibrations. The preliminary experiments show that the proposed algorithm is able to robustly generate environment maps. The algorithm is also suitable to be implemented as a vision system for autonomous mobile robots.

AB - In this study we propose a method for creating 3D map of real world environment by using 3D occupancy grids. The map is created by characterizing each grid associated with a certain area in the real world environment by utilizing multiple measurements using stereo vision and Bayesian inference. The proposed method can absorb the measurement uncertainties caused in the stereo matching process and in the system's calibrations. The preliminary experiments show that the proposed algorithm is able to robustly generate environment maps. The algorithm is also suitable to be implemented as a vision system for autonomous mobile robots.

KW - Bayesian inference

KW - Mapping

KW - Mobile robots

KW - Occupancy grids

KW - Stereo vision

UR - http://www.scopus.com/inward/record.url?scp=17644412004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17644412004&partnerID=8YFLogxK

U2 - 10.1117/12.580585

DO - 10.1117/12.580585

M3 - Conference contribution

AN - SCOPUS:17644412004

VL - 5603

SP - 111

EP - 118

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Kaneko, S.

A2 - Cho, H.

A2 - Knopf, G.K.

A2 - Tutsch, R.

T2 - Machine Vision and its Optomechatronic Applications

Y2 - 26 October 2004 through 28 October 2004

ER -

Three-dimensional mapping utilizing stereo vision and Bayesian inference

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this