On feature extraction and region matching for forward scan sonar imaging

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Citations (Scopus)

Abstract

Automated processing of sonar video imagery enables valuable capabilities for a wide variety of underwater applications in turbid environments. Some key examples comprise the detection, localization and tracking of distinct scene targets, building feature maps, as well as improving positioning accuracy of unmanned submarines by means of image registration and 3D motion estimation to augment traditional positioning devices. This work offers a novel technique for the registration of 2D forward-look sonar images, by optimization over the sonar 3D motion parameters. It incorporates landmark detection through an adaptive clustering scheme with Gaussian map to represent key features at each frame. Improved performance is demonstrated in experiments with real data, both in terms of computation time and accuracy, relative to the state of the art, where the registration utilizes a simplified 2D image transformation model. Among many potentials, the method can improve precision in AUV navigation and environmental modeling.

Original languageEnglish
Title of host publicationOCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean
DOIs
StatePublished - Dec 1 2012
EventOCEANS 2012 MTS/IEEE Hampton Roads Conference: Harnessing the Power of the Ocean - Virginia Beach, VA, United States
Duration: Oct 14 2012Oct 19 2012

Other

OtherOCEANS 2012 MTS/IEEE Hampton Roads Conference: Harnessing the Power of the Ocean
CountryUnited States
CityVirginia Beach, VA
Period10/14/1210/19/12

Fingerprint

Sonar
Feature extraction
Imaging techniques
Image registration
Motion estimation
Navigation
Processing
Experiments

ASJC Scopus subject areas

  • Ocean Engineering

Cite this

Aykin, M. D., & Negahdaripour, S. (2012). On feature extraction and region matching for forward scan sonar imaging. In OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean [6404983] https://doi.org/10.1109/OCEANS.2012.6404983

On feature extraction and region matching for forward scan sonar imaging. / Aykin, M. D.; Negahdaripour, Shahriar.

OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean. 2012. 6404983.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Aykin, MD & Negahdaripour, S 2012, On feature extraction and region matching for forward scan sonar imaging. in OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean., 6404983, OCEANS 2012 MTS/IEEE Hampton Roads Conference: Harnessing the Power of the Ocean, Virginia Beach, VA, United States, 10/14/12. https://doi.org/10.1109/OCEANS.2012.6404983
Aykin, M. D. ; Negahdaripour, Shahriar. / On feature extraction and region matching for forward scan sonar imaging. OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean. 2012.
@inproceedings{31abee9118544cec98b5adbbb2f58e50,
title = "On feature extraction and region matching for forward scan sonar imaging",
abstract = "Automated processing of sonar video imagery enables valuable capabilities for a wide variety of underwater applications in turbid environments. Some key examples comprise the detection, localization and tracking of distinct scene targets, building feature maps, as well as improving positioning accuracy of unmanned submarines by means of image registration and 3D motion estimation to augment traditional positioning devices. This work offers a novel technique for the registration of 2D forward-look sonar images, by optimization over the sonar 3D motion parameters. It incorporates landmark detection through an adaptive clustering scheme with Gaussian map to represent key features at each frame. Improved performance is demonstrated in experiments with real data, both in terms of computation time and accuracy, relative to the state of the art, where the registration utilizes a simplified 2D image transformation model. Among many potentials, the method can improve precision in AUV navigation and environmental modeling.",
author = "Aykin, {M. D.} and Shahriar Negahdaripour",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/OCEANS.2012.6404983",
language = "English",
isbn = "9781467308298",
booktitle = "OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean",

}

TY - GEN

T1 - On feature extraction and region matching for forward scan sonar imaging

AU - Aykin, M. D.

AU - Negahdaripour, Shahriar

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Automated processing of sonar video imagery enables valuable capabilities for a wide variety of underwater applications in turbid environments. Some key examples comprise the detection, localization and tracking of distinct scene targets, building feature maps, as well as improving positioning accuracy of unmanned submarines by means of image registration and 3D motion estimation to augment traditional positioning devices. This work offers a novel technique for the registration of 2D forward-look sonar images, by optimization over the sonar 3D motion parameters. It incorporates landmark detection through an adaptive clustering scheme with Gaussian map to represent key features at each frame. Improved performance is demonstrated in experiments with real data, both in terms of computation time and accuracy, relative to the state of the art, where the registration utilizes a simplified 2D image transformation model. Among many potentials, the method can improve precision in AUV navigation and environmental modeling.

AB - Automated processing of sonar video imagery enables valuable capabilities for a wide variety of underwater applications in turbid environments. Some key examples comprise the detection, localization and tracking of distinct scene targets, building feature maps, as well as improving positioning accuracy of unmanned submarines by means of image registration and 3D motion estimation to augment traditional positioning devices. This work offers a novel technique for the registration of 2D forward-look sonar images, by optimization over the sonar 3D motion parameters. It incorporates landmark detection through an adaptive clustering scheme with Gaussian map to represent key features at each frame. Improved performance is demonstrated in experiments with real data, both in terms of computation time and accuracy, relative to the state of the art, where the registration utilizes a simplified 2D image transformation model. Among many potentials, the method can improve precision in AUV navigation and environmental modeling.

UR - http://www.scopus.com/inward/record.url?scp=84873591910&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873591910&partnerID=8YFLogxK

U2 - 10.1109/OCEANS.2012.6404983

DO - 10.1109/OCEANS.2012.6404983

M3 - Conference contribution

SN - 9781467308298

BT - OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean

ER -