Improved range estimation and underwater image enhancement under turbidity by opti-acoustic stereo imaging

Mohammadreza Babaee, Shahriar Negahdaripour

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

4 Citations (Scopus)

Abstract

Images recorded in turbid waters suffer from various forms of signal degradation due to light absorption, scattering and backscatter. Much of the earlier work to enhance color, contrast and sharpness follow the single-image dehazing approach from the atmospheric imaging literature. Requiring knowledge of both range to scene objects and ambient lighting, various techniques differ in how they estimate the information from various image regions. Moreover, some assumptions are made that hold for most images recorded in air and clear waters, but are often violated in turbid environments, leading to poor results. Alternatively, stereo imaging and polarization have been explored for simultaneous range estimating and image dehazing, however, these can become ineffective with low visibility and (or) weak polarization cue. This work explores a methodology that utilizes the visual cues in multi-modal optical and sonar images, namely, the occluding contours of various scene objects that can be detected and matched more robustly than point features. Calculating the sparse 3-D positions of these contours from opti-acosutic stereo data, we infer a dense range map by exploiting an MRF-based statistical framework, where image intensities and range values serve as observation and hidden variables. Additionally, the opti-acoustic epipolar geometry guides the inference of the MRF by refining neighborhood pixels. The improved performance over other state-of-the-art techniques is demonstrated using images recorded under different turbidity conditions.

Original languageEnglish (US)
Title of host publicationMTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479987368
DOIs
StatePublished - Sep 17 2015
EventMTS/IEEE OCEANS 2015 - Genova - Genova, Italy
Duration: May 18 2015May 21 2015

Other

OtherMTS/IEEE OCEANS 2015 - Genova
CountryItaly
CityGenova
Period5/18/155/21/15

Fingerprint

Image enhancement
Turbidity
turbidity
acoustics
Acoustics
Polarization
Imaging techniques
Sonar
Visibility
Light absorption
Refining
Water
Lighting
Pixels
Scattering
Color
Degradation
Geometry
Air
polarization

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Oceanography

Cite this

Babaee, M., & Negahdaripour, S. (2015). Improved range estimation and underwater image enhancement under turbidity by opti-acoustic stereo imaging. In MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World [7271611] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/OCEANS-Genova.2015.7271611

Improved range estimation and underwater image enhancement under turbidity by opti-acoustic stereo imaging. / Babaee, Mohammadreza; Negahdaripour, Shahriar.

MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World. Institute of Electrical and Electronics Engineers Inc., 2015. 7271611.

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

Babaee, M & Negahdaripour, S 2015, Improved range estimation and underwater image enhancement under turbidity by opti-acoustic stereo imaging. in MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World., 7271611, Institute of Electrical and Electronics Engineers Inc., MTS/IEEE OCEANS 2015 - Genova, Genova, Italy, 5/18/15. https://doi.org/10.1109/OCEANS-Genova.2015.7271611
Babaee M, Negahdaripour S. Improved range estimation and underwater image enhancement under turbidity by opti-acoustic stereo imaging. In MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World. Institute of Electrical and Electronics Engineers Inc. 2015. 7271611 https://doi.org/10.1109/OCEANS-Genova.2015.7271611
Babaee, Mohammadreza ; Negahdaripour, Shahriar. / Improved range estimation and underwater image enhancement under turbidity by opti-acoustic stereo imaging. MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{387de98009e64b75ba982ce803a0fac3,
title = "Improved range estimation and underwater image enhancement under turbidity by opti-acoustic stereo imaging",
abstract = "Images recorded in turbid waters suffer from various forms of signal degradation due to light absorption, scattering and backscatter. Much of the earlier work to enhance color, contrast and sharpness follow the single-image dehazing approach from the atmospheric imaging literature. Requiring knowledge of both range to scene objects and ambient lighting, various techniques differ in how they estimate the information from various image regions. Moreover, some assumptions are made that hold for most images recorded in air and clear waters, but are often violated in turbid environments, leading to poor results. Alternatively, stereo imaging and polarization have been explored for simultaneous range estimating and image dehazing, however, these can become ineffective with low visibility and (or) weak polarization cue. This work explores a methodology that utilizes the visual cues in multi-modal optical and sonar images, namely, the occluding contours of various scene objects that can be detected and matched more robustly than point features. Calculating the sparse 3-D positions of these contours from opti-acosutic stereo data, we infer a dense range map by exploiting an MRF-based statistical framework, where image intensities and range values serve as observation and hidden variables. Additionally, the opti-acoustic epipolar geometry guides the inference of the MRF by refining neighborhood pixels. The improved performance over other state-of-the-art techniques is demonstrated using images recorded under different turbidity conditions.",
author = "Mohammadreza Babaee and Shahriar Negahdaripour",
year = "2015",
month = "9",
day = "17",
doi = "10.1109/OCEANS-Genova.2015.7271611",
language = "English (US)",
isbn = "9781479987368",
booktitle = "MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Improved range estimation and underwater image enhancement under turbidity by opti-acoustic stereo imaging

AU - Babaee, Mohammadreza

AU - Negahdaripour, Shahriar

PY - 2015/9/17

Y1 - 2015/9/17

N2 - Images recorded in turbid waters suffer from various forms of signal degradation due to light absorption, scattering and backscatter. Much of the earlier work to enhance color, contrast and sharpness follow the single-image dehazing approach from the atmospheric imaging literature. Requiring knowledge of both range to scene objects and ambient lighting, various techniques differ in how they estimate the information from various image regions. Moreover, some assumptions are made that hold for most images recorded in air and clear waters, but are often violated in turbid environments, leading to poor results. Alternatively, stereo imaging and polarization have been explored for simultaneous range estimating and image dehazing, however, these can become ineffective with low visibility and (or) weak polarization cue. This work explores a methodology that utilizes the visual cues in multi-modal optical and sonar images, namely, the occluding contours of various scene objects that can be detected and matched more robustly than point features. Calculating the sparse 3-D positions of these contours from opti-acosutic stereo data, we infer a dense range map by exploiting an MRF-based statistical framework, where image intensities and range values serve as observation and hidden variables. Additionally, the opti-acoustic epipolar geometry guides the inference of the MRF by refining neighborhood pixels. The improved performance over other state-of-the-art techniques is demonstrated using images recorded under different turbidity conditions.

AB - Images recorded in turbid waters suffer from various forms of signal degradation due to light absorption, scattering and backscatter. Much of the earlier work to enhance color, contrast and sharpness follow the single-image dehazing approach from the atmospheric imaging literature. Requiring knowledge of both range to scene objects and ambient lighting, various techniques differ in how they estimate the information from various image regions. Moreover, some assumptions are made that hold for most images recorded in air and clear waters, but are often violated in turbid environments, leading to poor results. Alternatively, stereo imaging and polarization have been explored for simultaneous range estimating and image dehazing, however, these can become ineffective with low visibility and (or) weak polarization cue. This work explores a methodology that utilizes the visual cues in multi-modal optical and sonar images, namely, the occluding contours of various scene objects that can be detected and matched more robustly than point features. Calculating the sparse 3-D positions of these contours from opti-acosutic stereo data, we infer a dense range map by exploiting an MRF-based statistical framework, where image intensities and range values serve as observation and hidden variables. Additionally, the opti-acoustic epipolar geometry guides the inference of the MRF by refining neighborhood pixels. The improved performance over other state-of-the-art techniques is demonstrated using images recorded under different turbidity conditions.

UR - http://www.scopus.com/inward/record.url?scp=84957625489&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957625489&partnerID=8YFLogxK

U2 - 10.1109/OCEANS-Genova.2015.7271611

DO - 10.1109/OCEANS-Genova.2015.7271611

M3 - Conference contribution

AN - SCOPUS:84957625489

SN - 9781479987368

BT - MTS/IEEE OCEANS 2015 - Genova: Discovering Sustainable Ocean Energy for a New World

PB - Institute of Electrical and Electronics Engineers Inc.

ER -