Robust optical flow estimation using underwater colair images

Shahriar Negahdaripour, Hossein Madjidi

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

1 Citation (Scopus)

Abstract

Accurate and efficient optical flow estimation is a major step in many computational vision problems, including 3-D mapping applications. While processing of gray scale image sequences has been the main approach, some authors have recently investigated and reported the use of color images. The main advantage in the use of color images is to exploit redundant information at each pixel, namely 3 channels, as potential cues for visual 'motion. Moreover, several spectral-dependent factors including medium attenuation may justify the use of color cues in underwater, calling for a physics-based approach to optical flow analysis. This paper explores a simplified underwater image formation model l) to provide some preliminary insight on the information encoded in various color channels, 2) draw some general conclusions on the use of color and its various representations, and 3) verify if the results are consistent with the experiments with 7 sets of coral reef video moded in relatively clear shallow waters of the Bahamas. These results suggest that optical flow algorithms based on the HSV representation can provide improved localization and accuracy.

Original languageEnglish (US)
Title of host publicationOceans 2003: Celebrating the Past... Teaming Toward the Future
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2309-2316
Number of pages8
Volume4
ISBN (Print)0933957300, 9780933957305
DOIs
StatePublished - 2003
EventOceans 2003 - Marine Technology Society, Institute of Electrical and Electronics Engineers Conference, MTS/IEEE - San Diego, United States
Duration: Sep 22 2003Sep 26 2003

Other

OtherOceans 2003 - Marine Technology Society, Institute of Electrical and Electronics Engineers Conference, MTS/IEEE
CountryUnited States
CitySan Diego
Period9/22/039/26/03

Fingerprint

Optical flows
Color
Reefs
Image processing
Physics
Pixels
Processing
Water
Experiments

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

Negahdaripour, S., & Madjidi, H. (2003). Robust optical flow estimation using underwater colair images. In Oceans 2003: Celebrating the Past... Teaming Toward the Future (Vol. 4, pp. 2309-2316). [1282854] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/OCEANS.2003.178269

Robust optical flow estimation using underwater colair images. / Negahdaripour, Shahriar; Madjidi, Hossein.

Oceans 2003: Celebrating the Past... Teaming Toward the Future. Vol. 4 Institute of Electrical and Electronics Engineers Inc., 2003. p. 2309-2316 1282854.

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

Negahdaripour, S & Madjidi, H 2003, Robust optical flow estimation using underwater colair images. in Oceans 2003: Celebrating the Past... Teaming Toward the Future. vol. 4, 1282854, Institute of Electrical and Electronics Engineers Inc., pp. 2309-2316, Oceans 2003 - Marine Technology Society, Institute of Electrical and Electronics Engineers Conference, MTS/IEEE, San Diego, United States, 9/22/03. https://doi.org/10.1109/OCEANS.2003.178269
Negahdaripour S, Madjidi H. Robust optical flow estimation using underwater colair images. In Oceans 2003: Celebrating the Past... Teaming Toward the Future. Vol. 4. Institute of Electrical and Electronics Engineers Inc. 2003. p. 2309-2316. 1282854 https://doi.org/10.1109/OCEANS.2003.178269
Negahdaripour, Shahriar ; Madjidi, Hossein. / Robust optical flow estimation using underwater colair images. Oceans 2003: Celebrating the Past... Teaming Toward the Future. Vol. 4 Institute of Electrical and Electronics Engineers Inc., 2003. pp. 2309-2316
@inproceedings{00e0a42af63246df8bbcabf525e45d47,
title = "Robust optical flow estimation using underwater colair images",
abstract = "Accurate and efficient optical flow estimation is a major step in many computational vision problems, including 3-D mapping applications. While processing of gray scale image sequences has been the main approach, some authors have recently investigated and reported the use of color images. The main advantage in the use of color images is to exploit redundant information at each pixel, namely 3 channels, as potential cues for visual 'motion. Moreover, several spectral-dependent factors including medium attenuation may justify the use of color cues in underwater, calling for a physics-based approach to optical flow analysis. This paper explores a simplified underwater image formation model l) to provide some preliminary insight on the information encoded in various color channels, 2) draw some general conclusions on the use of color and its various representations, and 3) verify if the results are consistent with the experiments with 7 sets of coral reef video moded in relatively clear shallow waters of the Bahamas. These results suggest that optical flow algorithms based on the HSV representation can provide improved localization and accuracy.",
author = "Shahriar Negahdaripour and Hossein Madjidi",
year = "2003",
doi = "10.1109/OCEANS.2003.178269",
language = "English (US)",
isbn = "0933957300",
volume = "4",
pages = "2309--2316",
booktitle = "Oceans 2003: Celebrating the Past... Teaming Toward the Future",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Robust optical flow estimation using underwater colair images

AU - Negahdaripour, Shahriar

AU - Madjidi, Hossein

PY - 2003

Y1 - 2003

N2 - Accurate and efficient optical flow estimation is a major step in many computational vision problems, including 3-D mapping applications. While processing of gray scale image sequences has been the main approach, some authors have recently investigated and reported the use of color images. The main advantage in the use of color images is to exploit redundant information at each pixel, namely 3 channels, as potential cues for visual 'motion. Moreover, several spectral-dependent factors including medium attenuation may justify the use of color cues in underwater, calling for a physics-based approach to optical flow analysis. This paper explores a simplified underwater image formation model l) to provide some preliminary insight on the information encoded in various color channels, 2) draw some general conclusions on the use of color and its various representations, and 3) verify if the results are consistent with the experiments with 7 sets of coral reef video moded in relatively clear shallow waters of the Bahamas. These results suggest that optical flow algorithms based on the HSV representation can provide improved localization and accuracy.

AB - Accurate and efficient optical flow estimation is a major step in many computational vision problems, including 3-D mapping applications. While processing of gray scale image sequences has been the main approach, some authors have recently investigated and reported the use of color images. The main advantage in the use of color images is to exploit redundant information at each pixel, namely 3 channels, as potential cues for visual 'motion. Moreover, several spectral-dependent factors including medium attenuation may justify the use of color cues in underwater, calling for a physics-based approach to optical flow analysis. This paper explores a simplified underwater image formation model l) to provide some preliminary insight on the information encoded in various color channels, 2) draw some general conclusions on the use of color and its various representations, and 3) verify if the results are consistent with the experiments with 7 sets of coral reef video moded in relatively clear shallow waters of the Bahamas. These results suggest that optical flow algorithms based on the HSV representation can provide improved localization and accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84945551186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945551186&partnerID=8YFLogxK

U2 - 10.1109/OCEANS.2003.178269

DO - 10.1109/OCEANS.2003.178269

M3 - Conference contribution

SN - 0933957300

SN - 9780933957305

VL - 4

SP - 2309

EP - 2316

BT - Oceans 2003: Celebrating the Past... Teaming Toward the Future

PB - Institute of Electrical and Electronics Engineers Inc.

ER -