Monocular ORB-SLAM application in underwater scenarios

Franco Hidalgo Herencia; Chris Kahlefendt; Thomas Braunl

doi:10.1109/OCEANSKOBE.2018.8559435

Monocular ORB-SLAM application in underwater scenarios

Franco Hidalgo Herencia, Chris Kahlefendt, Thomas Braunl

Research output: Contribution to conference › Conference Paper › peer-review

4 Scopus citations

Abstract

This paper presents an experimental evaluation of monocular ORB-SLAM applied to underwater scenarios. It is investigated as an alternative SLAM method with minimal instu-mentation compared to other approaches that integrate different sensors such as inertial and acoustic sensors. ORB-SLAM creates a 3D map based on image frames and estimates the position of the robot by using a feature-based front-end and a graph-based back-end. The performance of ORB-SLAM is evaluated through experiments in different settings with varying lighting, visibility and water dynamics. Results show good performance given the right conditions and demonstrate that ORB-SLAM can work well in the underwater environment. Based on our findings the paper outlines possible enhancements which should further improve on the algorithms performance.

Original language	American English
DOIs	https://doi.org/10.1109/OCEANSKOBE.2018.8559435 https://doi.org/10.1109/OCEANSKOBE.2018.8559435
State	Published - 4 Dec 2018
Externally published	Yes
Event	2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, OCEANS - Kobe 2018 - Kobe, Japan Duration: 28 May 2018 → 31 May 2018

Conference

Conference	2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, OCEANS - Kobe 2018
Country/Territory	Japan
City	Kobe
Period	28/05/18 → 31/05/18

Access to Document

Cite this

@conference{0779b6a72bb24ade8b0d5fe5bb948417,

title = "Monocular ORB-SLAM application in underwater scenarios",

abstract = "This paper presents an experimental evaluation of monocular ORB-SLAM applied to underwater scenarios. It is investigated as an alternative SLAM method with minimal instu-mentation compared to other approaches that integrate different sensors such as inertial and acoustic sensors. ORB-SLAM creates a 3D map based on image frames and estimates the position of the robot by using a feature-based front-end and a graph-based back-end. The performance of ORB-SLAM is evaluated through experiments in different settings with varying lighting, visibility and water dynamics. Results show good performance given the right conditions and demonstrate that ORB-SLAM can work well in the underwater environment. Based on our findings the paper outlines possible enhancements which should further improve on the algorithms performance.",

author = "{Hidalgo Herencia}, Franco and Chris Kahlefendt and Thomas Braunl",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, OCEANS - Kobe 2018 ; Conference date: 28-05-2018 Through 31-05-2018",

year = "2018",

month = dec,

day = "4",

doi = "10.1109/OCEANSKOBE.2018.8559435",

language = "American English",

}

TY - CONF

T1 - Monocular ORB-SLAM application in underwater scenarios

AU - Hidalgo Herencia, Franco

AU - Kahlefendt, Chris

AU - Braunl, Thomas

PY - 2018/12/4

Y1 - 2018/12/4

N2 - This paper presents an experimental evaluation of monocular ORB-SLAM applied to underwater scenarios. It is investigated as an alternative SLAM method with minimal instu-mentation compared to other approaches that integrate different sensors such as inertial and acoustic sensors. ORB-SLAM creates a 3D map based on image frames and estimates the position of the robot by using a feature-based front-end and a graph-based back-end. The performance of ORB-SLAM is evaluated through experiments in different settings with varying lighting, visibility and water dynamics. Results show good performance given the right conditions and demonstrate that ORB-SLAM can work well in the underwater environment. Based on our findings the paper outlines possible enhancements which should further improve on the algorithms performance.

AB - This paper presents an experimental evaluation of monocular ORB-SLAM applied to underwater scenarios. It is investigated as an alternative SLAM method with minimal instu-mentation compared to other approaches that integrate different sensors such as inertial and acoustic sensors. ORB-SLAM creates a 3D map based on image frames and estimates the position of the robot by using a feature-based front-end and a graph-based back-end. The performance of ORB-SLAM is evaluated through experiments in different settings with varying lighting, visibility and water dynamics. Results show good performance given the right conditions and demonstrate that ORB-SLAM can work well in the underwater environment. Based on our findings the paper outlines possible enhancements which should further improve on the algorithms performance.

UR - http://www.scopus.com/inward/record.url?scp=85060305049&partnerID=8YFLogxK

U2 - 10.1109/OCEANSKOBE.2018.8559435

DO - 10.1109/OCEANSKOBE.2018.8559435

M3 - Conference Paper

T2 - 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, OCEANS - Kobe 2018

Y2 - 28 May 2018 through 31 May 2018

ER -

Monocular ORB-SLAM application in underwater scenarios

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this