Automated target recognition with SAS: Shadow and highlight-based classification

Olga Lopera; Yves Dupont

doi:10.1109/OCEANS.2012.6405117

Automated target recognition with SAS: Shadow and highlight-based classification

Olga Lopera
, Yves Dupont

Remote Sensing

Belgian Navy

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

12 Citations (Scopus)

Abstract

This paper presents an integrated technique for automated target recognition (ATR) in synthetic aperture sonar (SAS) images. The recognition procedure starts with a despeckling approach based on the anisotropic diffusion filter. As a second step, a fuzzymorpho-based segmentation procedure is applied to the filtered images, which partitions the image into highlights and shadow areas. A number of geometrical features are extracted from these areas, and are then used to classify targets using a Markov Chain Monte Carlo (MCMC) approach Very promising results are obtained.

Original language	English
Title of host publication	OCEANS 2012 MTS/IEEE
Subtitle of host publication	Harnessing the Power of the Ocean
DOIs	https://doi.org/10.1109/OCEANS.2012.6405117
Publication status	Published - 2012
Event	OCEANS 2012 MTS/IEEE Hampton Roads Conference: Harnessing the Power of the Ocean - Virginia Beach, VA, United States Duration: 14 Oct 2012 → 19 Oct 2012

Publication series

Name	OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean

Conference

Conference	OCEANS 2012 MTS/IEEE Hampton Roads Conference: Harnessing the Power of the Ocean
Country/Territory	United States
City	Virginia Beach, VA
Period	14/10/12 → 19/10/12

Keywords

Automated target recognition
image processing
synthetic aperture sonar

Access to Document

10.1109/OCEANS.2012.6405117

Cite this

@inproceedings{aead28285cdb47ddb72f7e0de0e6d716,

title = "Automated target recognition with SAS: Shadow and highlight-based classification",

abstract = "This paper presents an integrated technique for automated target recognition (ATR) in synthetic aperture sonar (SAS) images. The recognition procedure starts with a despeckling approach based on the anisotropic diffusion filter. As a second step, a fuzzymorpho-based segmentation procedure is applied to the filtered images, which partitions the image into highlights and shadow areas. A number of geometrical features are extracted from these areas, and are then used to classify targets using a Markov Chain Monte Carlo (MCMC) approach Very promising results are obtained.",

keywords = "Automated target recognition, image processing, synthetic aperture sonar",

author = "Olga Lopera and Yves Dupont",

year = "2012",

doi = "10.1109/OCEANS.2012.6405117",

language = "English",

isbn = "9781467308298",

series = "OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean",

booktitle = "OCEANS 2012 MTS/IEEE",

note = "OCEANS 2012 MTS/IEEE Hampton Roads Conference: Harnessing the Power of the Ocean ; Conference date: 14-10-2012 Through 19-10-2012",

}

Lopera, O & Dupont, Y 2012, Automated target recognition with SAS: Shadow and highlight-based classification. in OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean., 6405117, OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean, OCEANS 2012 MTS/IEEE Hampton Roads Conference: Harnessing the Power of the Ocean, Virginia Beach, VA, United States, 14/10/12. https://doi.org/10.1109/OCEANS.2012.6405117

TY - GEN

T1 - Automated target recognition with SAS

T2 - OCEANS 2012 MTS/IEEE Hampton Roads Conference: Harnessing the Power of the Ocean

AU - Lopera, Olga

AU - Dupont, Yves

PY - 2012

Y1 - 2012

N2 - This paper presents an integrated technique for automated target recognition (ATR) in synthetic aperture sonar (SAS) images. The recognition procedure starts with a despeckling approach based on the anisotropic diffusion filter. As a second step, a fuzzymorpho-based segmentation procedure is applied to the filtered images, which partitions the image into highlights and shadow areas. A number of geometrical features are extracted from these areas, and are then used to classify targets using a Markov Chain Monte Carlo (MCMC) approach Very promising results are obtained.

AB - This paper presents an integrated technique for automated target recognition (ATR) in synthetic aperture sonar (SAS) images. The recognition procedure starts with a despeckling approach based on the anisotropic diffusion filter. As a second step, a fuzzymorpho-based segmentation procedure is applied to the filtered images, which partitions the image into highlights and shadow areas. A number of geometrical features are extracted from these areas, and are then used to classify targets using a Markov Chain Monte Carlo (MCMC) approach Very promising results are obtained.

KW - Automated target recognition

KW - image processing

KW - synthetic aperture sonar

UR - https://www.scopus.com/pages/publications/84873605827

U2 - 10.1109/OCEANS.2012.6405117

DO - 10.1109/OCEANS.2012.6405117

M3 - Conference contribution

AN - SCOPUS:84873605827

SN - 9781467308298

T3 - OCEANS 2012 MTS/IEEE: Harnessing the Power of the Ocean

BT - OCEANS 2012 MTS/IEEE

Y2 - 14 October 2012 through 19 October 2012

ER -

Automated target recognition with SAS: Shadow and highlight-based classification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this