Side scan sonar based self-localization for small Autonomous Underwater Vehicles

Jan Petrich, Mark F. Brown, Jesse L. Pentzer, John P. Sustersic

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper presents the development and experimental validation of a side-scan sonar based self-localization algorithm for Autonomous Underwater Vehicles (AUVs). Different classes of visually salient features are continuously extracted from dual-frequency sonar imagery using machine perception and subsequently utilized to generate sparse bathymetric maps. The diversity within the feature set, i.e. features of different sizes and features extracted at different sonar operating frequencies, allows for robust multimodal feature matching. Highly robust navigation solutions are generated in real-time by matching newly acquired features to a previously generated reference map. For each feature class, feature matching is carried out in four dimensions correlating feature location as well as perceived intensity. Overall utility and technical claims have been validated using real-world sonar imagery collected using an Iver3 AUV platform.

Original languageEnglish (US)
Pages (from-to)221-226
Number of pages6
JournalOcean Engineering
Volume161
DOIs
StatePublished - Aug 1 2018

Fingerprint

Autonomous underwater vehicles
Sonar
Navigation

All Science Journal Classification (ASJC) codes

  • Environmental Engineering
  • Ocean Engineering

Cite this

@article{5d9ad053e96945adbc7a49d73d3fad3a,
title = "Side scan sonar based self-localization for small Autonomous Underwater Vehicles",
abstract = "This paper presents the development and experimental validation of a side-scan sonar based self-localization algorithm for Autonomous Underwater Vehicles (AUVs). Different classes of visually salient features are continuously extracted from dual-frequency sonar imagery using machine perception and subsequently utilized to generate sparse bathymetric maps. The diversity within the feature set, i.e. features of different sizes and features extracted at different sonar operating frequencies, allows for robust multimodal feature matching. Highly robust navigation solutions are generated in real-time by matching newly acquired features to a previously generated reference map. For each feature class, feature matching is carried out in four dimensions correlating feature location as well as perceived intensity. Overall utility and technical claims have been validated using real-world sonar imagery collected using an Iver3 AUV platform.",
author = "Jan Petrich and Brown, {Mark F.} and Pentzer, {Jesse L.} and Sustersic, {John P.}",
year = "2018",
month = "8",
day = "1",
doi = "10.1016/j.oceaneng.2018.04.095",
language = "English (US)",
volume = "161",
pages = "221--226",
journal = "Ocean Engineering",
issn = "0029-8018",
publisher = "Elsevier BV",

}

Side scan sonar based self-localization for small Autonomous Underwater Vehicles. / Petrich, Jan; Brown, Mark F.; Pentzer, Jesse L.; Sustersic, John P.

In: Ocean Engineering, Vol. 161, 01.08.2018, p. 221-226.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Side scan sonar based self-localization for small Autonomous Underwater Vehicles

AU - Petrich, Jan

AU - Brown, Mark F.

AU - Pentzer, Jesse L.

AU - Sustersic, John P.

PY - 2018/8/1

Y1 - 2018/8/1

N2 - This paper presents the development and experimental validation of a side-scan sonar based self-localization algorithm for Autonomous Underwater Vehicles (AUVs). Different classes of visually salient features are continuously extracted from dual-frequency sonar imagery using machine perception and subsequently utilized to generate sparse bathymetric maps. The diversity within the feature set, i.e. features of different sizes and features extracted at different sonar operating frequencies, allows for robust multimodal feature matching. Highly robust navigation solutions are generated in real-time by matching newly acquired features to a previously generated reference map. For each feature class, feature matching is carried out in four dimensions correlating feature location as well as perceived intensity. Overall utility and technical claims have been validated using real-world sonar imagery collected using an Iver3 AUV platform.

AB - This paper presents the development and experimental validation of a side-scan sonar based self-localization algorithm for Autonomous Underwater Vehicles (AUVs). Different classes of visually salient features are continuously extracted from dual-frequency sonar imagery using machine perception and subsequently utilized to generate sparse bathymetric maps. The diversity within the feature set, i.e. features of different sizes and features extracted at different sonar operating frequencies, allows for robust multimodal feature matching. Highly robust navigation solutions are generated in real-time by matching newly acquired features to a previously generated reference map. For each feature class, feature matching is carried out in four dimensions correlating feature location as well as perceived intensity. Overall utility and technical claims have been validated using real-world sonar imagery collected using an Iver3 AUV platform.

UR - http://www.scopus.com/inward/record.url?scp=85047255376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047255376&partnerID=8YFLogxK

U2 - 10.1016/j.oceaneng.2018.04.095

DO - 10.1016/j.oceaneng.2018.04.095

M3 - Article

AN - SCOPUS:85047255376

VL - 161

SP - 221

EP - 226

JO - Ocean Engineering

JF - Ocean Engineering

SN - 0029-8018

ER -