Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis

Mohammad Haghighat, Xiuying Li, Zicheng Fang, Yang Zhang, Shahriar Negahdaripour

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

1 Citation (Scopus)

Abstract

In this paper, we present methods for segmenting noisy two-dimensional forward-scan sonar images and classify and model their background. The segmentation approach differentiates the highlight blobs, cast shadows, and the background of sonar images. There is usually little information within relatively large background regions corresponding to the flat sea bottom and (or) water column, as they are often corrupted with speckle noise. Our experiments show that the background texture is dominated by the speckle noise which has the appearance of a pseudo-random texture. We show that the background texture of the underwater sonar images can be categorized by a small number of classes. The statistical features work better than the texture-based features in categorizing the pseudo-random background, which further strengthen our hypothesis of the dominance of noise over the background texture. As a result, we can model the noisy background with a few parameters. This has an application in coding the sonar images in which highlight blob regions and cast shadows are coded at the encoder side while the speckle noise-corrupted background can be synthesized at the decoder side. Since the background regions occupy a large fraction of the FS sonar image, we expect higher compression rates than most current image or video coding standards and other custom-designed sonar image compression techniques.

Original languageEnglish (US)
Title of host publicationOCEANS 2016 MTS/IEEE Monterey, OCE 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509015375
DOIs
StatePublished - Nov 28 2016
Event2016 OCEANS MTS/IEEE Monterey, OCE 2016 - Monterey, United States
Duration: Sep 19 2016Sep 23 2016

Other

Other2016 OCEANS MTS/IEEE Monterey, OCE 2016
CountryUnited States
CityMonterey
Period9/19/169/23/16

Fingerprint

sonar imagery
sonar
Sonar
imagery
segmentation
coding
Textures
textures
texture
synthesis
Speckle
speckle
modeling
Image coding
casts
compression
Image compression
decoders
background noise
coders

Keywords

  • Forward-scan sonar imagery
  • Sonar background classification
  • Sonar image segmentation
  • Speckle noise modeling and synthesis

ASJC Scopus subject areas

  • Instrumentation
  • Oceanography
  • Ocean Engineering

Cite this

Haghighat, M., Li, X., Fang, Z., Zhang, Y., & Negahdaripour, S. (2016). Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis. In OCEANS 2016 MTS/IEEE Monterey, OCE 2016 [7761408] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/OCEANS.2016.7761408

Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis. / Haghighat, Mohammad; Li, Xiuying; Fang, Zicheng; Zhang, Yang; Negahdaripour, Shahriar.

OCEANS 2016 MTS/IEEE Monterey, OCE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7761408.

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

Haghighat, M, Li, X, Fang, Z, Zhang, Y & Negahdaripour, S 2016, Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis. in OCEANS 2016 MTS/IEEE Monterey, OCE 2016., 7761408, Institute of Electrical and Electronics Engineers Inc., 2016 OCEANS MTS/IEEE Monterey, OCE 2016, Monterey, United States, 9/19/16. https://doi.org/10.1109/OCEANS.2016.7761408
Haghighat M, Li X, Fang Z, Zhang Y, Negahdaripour S. Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis. In OCEANS 2016 MTS/IEEE Monterey, OCE 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7761408 https://doi.org/10.1109/OCEANS.2016.7761408
Haghighat, Mohammad ; Li, Xiuying ; Fang, Zicheng ; Zhang, Yang ; Negahdaripour, Shahriar. / Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis. OCEANS 2016 MTS/IEEE Monterey, OCE 2016. Institute of Electrical and Electronics Engineers Inc., 2016.
@inproceedings{89ad559636cb4b3dacc6b420415972e3,
title = "Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis",
abstract = "In this paper, we present methods for segmenting noisy two-dimensional forward-scan sonar images and classify and model their background. The segmentation approach differentiates the highlight blobs, cast shadows, and the background of sonar images. There is usually little information within relatively large background regions corresponding to the flat sea bottom and (or) water column, as they are often corrupted with speckle noise. Our experiments show that the background texture is dominated by the speckle noise which has the appearance of a pseudo-random texture. We show that the background texture of the underwater sonar images can be categorized by a small number of classes. The statistical features work better than the texture-based features in categorizing the pseudo-random background, which further strengthen our hypothesis of the dominance of noise over the background texture. As a result, we can model the noisy background with a few parameters. This has an application in coding the sonar images in which highlight blob regions and cast shadows are coded at the encoder side while the speckle noise-corrupted background can be synthesized at the decoder side. Since the background regions occupy a large fraction of the FS sonar image, we expect higher compression rates than most current image or video coding standards and other custom-designed sonar image compression techniques.",
keywords = "Forward-scan sonar imagery, Sonar background classification, Sonar image segmentation, Speckle noise modeling and synthesis",
author = "Mohammad Haghighat and Xiuying Li and Zicheng Fang and Yang Zhang and Shahriar Negahdaripour",
year = "2016",
month = "11",
day = "28",
doi = "10.1109/OCEANS.2016.7761408",
language = "English (US)",
booktitle = "OCEANS 2016 MTS/IEEE Monterey, OCE 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Segmentation, classification and modeling of two-dimensional forward-scan sonar imagery for efficient coding and synthesis

AU - Haghighat, Mohammad

AU - Li, Xiuying

AU - Fang, Zicheng

AU - Zhang, Yang

AU - Negahdaripour, Shahriar

PY - 2016/11/28

Y1 - 2016/11/28

N2 - In this paper, we present methods for segmenting noisy two-dimensional forward-scan sonar images and classify and model their background. The segmentation approach differentiates the highlight blobs, cast shadows, and the background of sonar images. There is usually little information within relatively large background regions corresponding to the flat sea bottom and (or) water column, as they are often corrupted with speckle noise. Our experiments show that the background texture is dominated by the speckle noise which has the appearance of a pseudo-random texture. We show that the background texture of the underwater sonar images can be categorized by a small number of classes. The statistical features work better than the texture-based features in categorizing the pseudo-random background, which further strengthen our hypothesis of the dominance of noise over the background texture. As a result, we can model the noisy background with a few parameters. This has an application in coding the sonar images in which highlight blob regions and cast shadows are coded at the encoder side while the speckle noise-corrupted background can be synthesized at the decoder side. Since the background regions occupy a large fraction of the FS sonar image, we expect higher compression rates than most current image or video coding standards and other custom-designed sonar image compression techniques.

AB - In this paper, we present methods for segmenting noisy two-dimensional forward-scan sonar images and classify and model their background. The segmentation approach differentiates the highlight blobs, cast shadows, and the background of sonar images. There is usually little information within relatively large background regions corresponding to the flat sea bottom and (or) water column, as they are often corrupted with speckle noise. Our experiments show that the background texture is dominated by the speckle noise which has the appearance of a pseudo-random texture. We show that the background texture of the underwater sonar images can be categorized by a small number of classes. The statistical features work better than the texture-based features in categorizing the pseudo-random background, which further strengthen our hypothesis of the dominance of noise over the background texture. As a result, we can model the noisy background with a few parameters. This has an application in coding the sonar images in which highlight blob regions and cast shadows are coded at the encoder side while the speckle noise-corrupted background can be synthesized at the decoder side. Since the background regions occupy a large fraction of the FS sonar image, we expect higher compression rates than most current image or video coding standards and other custom-designed sonar image compression techniques.

KW - Forward-scan sonar imagery

KW - Sonar background classification

KW - Sonar image segmentation

KW - Speckle noise modeling and synthesis

UR - http://www.scopus.com/inward/record.url?scp=85006839994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006839994&partnerID=8YFLogxK

U2 - 10.1109/OCEANS.2016.7761408

DO - 10.1109/OCEANS.2016.7761408

M3 - Conference contribution

BT - OCEANS 2016 MTS/IEEE Monterey, OCE 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -