Dense 3D Map Construction for Indoor Search and Rescue

Lars-Peter Ellekilde, Shoudong Huang, Jaime Valls Miró, Gamini Dissanayake

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

 
Udgivelsesdato: Jan-Feb
OriginalsprogEngelsk
TidsskriftJournal of Field Robotics
Vol/bind24
Udgave nummer1-2
Sider (fra-til)71-89
Antal sider18
ISSN1556-4959
StatusUdgivet - 1. jan. 2007

Fingeraftryk

Cameras
Image sensors
Robotics
Sampling

Citer dette

Ellekilde, L-P., Huang, S., Miró, J. V., & Dissanayake, G. (2007). Dense 3D Map Construction for Indoor Search and Rescue. Journal of Field Robotics, 24(1-2), 71-89.
Ellekilde, Lars-Peter ; Huang, Shoudong ; Miró, Jaime Valls ; Dissanayake, Gamini. / Dense 3D Map Construction for Indoor Search and Rescue. I: Journal of Field Robotics. 2007 ; Bind 24, Nr. 1-2. s. 71-89.
@article{88eacbf0cb3011dc8674000ea68e967b,
title = "Dense 3D Map Construction for Indoor Search and Rescue",
abstract = "The main contribution of this paper is a new simultaneous localization and mapping SLAM algorithm for building dense three-dimensional maps using information ac-quired from a range imager and a conventional camera, for robotic search and rescue inunstructured indoor environments. A key challenge in this scenario is that the robotmoves in 6D and no odometry information is available. An extended information ?lter EIF is used to estimate the state vector containing the sequence of camera poses andsome selected 3D point features in the environment. Data association is performed usinga combination of scale invariant feature transformation SIFT feature detection andmatching, random sampling consensus RANSAC , and least square 3D point sets ?tting.Experimental results are provided to demonstrate the effectiveness of the techniquesdeveloped.",
author = "Lars-Peter Ellekilde and Shoudong Huang and Mir{\'o}, {Jaime Valls} and Gamini Dissanayake",
year = "2007",
month = "1",
day = "1",
language = "English",
volume = "24",
pages = "71--89",
journal = "Journal of Field Robotics",
issn = "1556-4959",
publisher = "JohnWiley & Sons, Inc.",
number = "1-2",

}

Ellekilde, L-P, Huang, S, Miró, JV & Dissanayake, G 2007, 'Dense 3D Map Construction for Indoor Search and Rescue', Journal of Field Robotics, bind 24, nr. 1-2, s. 71-89.

Dense 3D Map Construction for Indoor Search and Rescue. / Ellekilde, Lars-Peter; Huang, Shoudong; Miró, Jaime Valls; Dissanayake, Gamini.

I: Journal of Field Robotics, Bind 24, Nr. 1-2, 01.01.2007, s. 71-89.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Dense 3D Map Construction for Indoor Search and Rescue

AU - Ellekilde, Lars-Peter

AU - Huang, Shoudong

AU - Miró, Jaime Valls

AU - Dissanayake, Gamini

PY - 2007/1/1

Y1 - 2007/1/1

N2 - The main contribution of this paper is a new simultaneous localization and mapping SLAM algorithm for building dense three-dimensional maps using information ac-quired from a range imager and a conventional camera, for robotic search and rescue inunstructured indoor environments. A key challenge in this scenario is that the robotmoves in 6D and no odometry information is available. An extended information ?lter EIF is used to estimate the state vector containing the sequence of camera poses andsome selected 3D point features in the environment. Data association is performed usinga combination of scale invariant feature transformation SIFT feature detection andmatching, random sampling consensus RANSAC , and least square 3D point sets ?tting.Experimental results are provided to demonstrate the effectiveness of the techniquesdeveloped.

AB - The main contribution of this paper is a new simultaneous localization and mapping SLAM algorithm for building dense three-dimensional maps using information ac-quired from a range imager and a conventional camera, for robotic search and rescue inunstructured indoor environments. A key challenge in this scenario is that the robotmoves in 6D and no odometry information is available. An extended information ?lter EIF is used to estimate the state vector containing the sequence of camera poses andsome selected 3D point features in the environment. Data association is performed usinga combination of scale invariant feature transformation SIFT feature detection andmatching, random sampling consensus RANSAC , and least square 3D point sets ?tting.Experimental results are provided to demonstrate the effectiveness of the techniquesdeveloped.

M3 - Journal article

VL - 24

SP - 71

EP - 89

JO - Journal of Field Robotics

JF - Journal of Field Robotics

SN - 1556-4959

IS - 1-2

ER -

Ellekilde L-P, Huang S, Miró JV, Dissanayake G. Dense 3D Map Construction for Indoor Search and Rescue. Journal of Field Robotics. 2007 jan 1;24(1-2):71-89.