Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles

Joaquim Salvi; Yvan Petillot; Elisabet Batlle

doi:10.1109/IROS.2008.4650627

Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles

Joaquim Salvi, Yvan Petillot, Elisabet Batlle

School of Engineering & Physical Sciences

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

22 Citations (Scopus)

Abstract

This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed. ©2008 IEEE.

Original language	English
Title of host publication	2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Pages	1011-1016
Number of pages	6
DOIs	https://doi.org/10.1109/IROS.2008.4650627
Publication status	Published - 2008
Event	21st IEEE/RSJ International Conference on Intelligent Robots and Systems 2008 - Nice, France Duration: 22 Sept 2008 → 26 Sept 2008

Conference

Conference	21st IEEE/RSJ International Conference on Intelligent Robots and Systems 2008
Abbreviated title	IROS 2008
Country/Territory	France
City	Nice
Period	22/09/08 → 26/09/08

Access to Document

10.1109/IROS.2008.4650627

Cite this

@inproceedings{6f5e4ded25d645eebe7a0a7a09c1a1c6,

title = "Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles",

abstract = "This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed. {\textcopyright}2008 IEEE.",

author = "Joaquim Salvi and Yvan Petillot and Elisabet Batlle",

year = "2008",

doi = "10.1109/IROS.2008.4650627",

language = "English",

isbn = "9781424420582",

pages = "1011--1016",

booktitle = "2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS",

note = "21st IEEE/RSJ International Conference on Intelligent Robots and Systems 2008, IROS 2008 ; Conference date: 22-09-2008 Through 26-09-2008",

}

TY - GEN

T1 - Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles

AU - Salvi, Joaquim

AU - Petillot, Yvan

AU - Batlle, Elisabet

PY - 2008

Y1 - 2008

N2 - This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed. ©2008 IEEE.

AB - This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed. ©2008 IEEE.

UR - http://www.scopus.com/inward/record.url?scp=69549116342&partnerID=8YFLogxK

U2 - 10.1109/IROS.2008.4650627

DO - 10.1109/IROS.2008.4650627

M3 - Conference contribution

SN - 9781424420582

SP - 1011

EP - 1016

BT - 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

T2 - 21st IEEE/RSJ International Conference on Intelligent Robots and Systems 2008

Y2 - 22 September 2008 through 26 September 2008

ER -

Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this