On feature matching and image registration for two-dimensional forward-scan sonar imaging

Murat D. Aykin, Shahriar Negahdaripour

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

The computer processing of forward-look sonar video imagery enables significant capabilities in a wide variety of underwater operations within turbid environments. Accurate automated registration of sonar video images to complement measurements from traditional positioning devices can be instrumental in the detection, localization, and tracking of distinct scene targets, building feature maps, change detection, as well as improving precision in the positioning of unmanned submarines. This work offers a novel solution for the registration of two-dimensional (2-D) forward-look sonar images recorded from a mobile platform, by optimization over the sonar 3-D motion parameters. It incorporates the detection of key features and landmarks, and effectively represents them with Gaussian maps. Improved performance is demonstrated with respect to the state-of-the-art approach utilizing 2-D similarity transformation, based on experiments with real data.

Original languageEnglish
Pages (from-to)602-623
Number of pages22
JournalJournal of Field Robotics
Volume30
Issue number4
DOIs
StatePublished - Jul 1 2013

Fingerprint

Image registration
Sonar
Imaging techniques
Processing
Experiments

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications

Cite this

On feature matching and image registration for two-dimensional forward-scan sonar imaging. / Aykin, Murat D.; Negahdaripour, Shahriar.

In: Journal of Field Robotics, Vol. 30, No. 4, 01.07.2013, p. 602-623.

Research output: Contribution to journalArticle

@article{e999184e9a424db78541c29d82597c82,
title = "On feature matching and image registration for two-dimensional forward-scan sonar imaging",
abstract = "The computer processing of forward-look sonar video imagery enables significant capabilities in a wide variety of underwater operations within turbid environments. Accurate automated registration of sonar video images to complement measurements from traditional positioning devices can be instrumental in the detection, localization, and tracking of distinct scene targets, building feature maps, change detection, as well as improving precision in the positioning of unmanned submarines. This work offers a novel solution for the registration of two-dimensional (2-D) forward-look sonar images recorded from a mobile platform, by optimization over the sonar 3-D motion parameters. It incorporates the detection of key features and landmarks, and effectively represents them with Gaussian maps. Improved performance is demonstrated with respect to the state-of-the-art approach utilizing 2-D similarity transformation, based on experiments with real data.",
author = "Aykin, {Murat D.} and Shahriar Negahdaripour",
year = "2013",
month = "7",
day = "1",
doi = "10.1002/rob.21461",
language = "English",
volume = "30",
pages = "602--623",
journal = "Journal of Field Robotics",
issn = "1556-4959",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

TY - JOUR

T1 - On feature matching and image registration for two-dimensional forward-scan sonar imaging

AU - Aykin, Murat D.

AU - Negahdaripour, Shahriar

PY - 2013/7/1

Y1 - 2013/7/1

N2 - The computer processing of forward-look sonar video imagery enables significant capabilities in a wide variety of underwater operations within turbid environments. Accurate automated registration of sonar video images to complement measurements from traditional positioning devices can be instrumental in the detection, localization, and tracking of distinct scene targets, building feature maps, change detection, as well as improving precision in the positioning of unmanned submarines. This work offers a novel solution for the registration of two-dimensional (2-D) forward-look sonar images recorded from a mobile platform, by optimization over the sonar 3-D motion parameters. It incorporates the detection of key features and landmarks, and effectively represents them with Gaussian maps. Improved performance is demonstrated with respect to the state-of-the-art approach utilizing 2-D similarity transformation, based on experiments with real data.

AB - The computer processing of forward-look sonar video imagery enables significant capabilities in a wide variety of underwater operations within turbid environments. Accurate automated registration of sonar video images to complement measurements from traditional positioning devices can be instrumental in the detection, localization, and tracking of distinct scene targets, building feature maps, change detection, as well as improving precision in the positioning of unmanned submarines. This work offers a novel solution for the registration of two-dimensional (2-D) forward-look sonar images recorded from a mobile platform, by optimization over the sonar 3-D motion parameters. It incorporates the detection of key features and landmarks, and effectively represents them with Gaussian maps. Improved performance is demonstrated with respect to the state-of-the-art approach utilizing 2-D similarity transformation, based on experiments with real data.

UR - http://www.scopus.com/inward/record.url?scp=84878840473&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878840473&partnerID=8YFLogxK

U2 - 10.1002/rob.21461

DO - 10.1002/rob.21461

M3 - Article

AN - SCOPUS:84878840473

VL - 30

SP - 602

EP - 623

JO - Journal of Field Robotics

JF - Journal of Field Robotics

SN - 1556-4959

IS - 4

ER -