Uncalibrated computer vision techniques in the underwater environment

K. Plakas, E. Trucco

Research output: Contribution to journalArticle

Abstract

Uncalibrated computer vision is a relatively new but fast growing area of computer vision research. Until recently, computer vision research has focused mainly on calibrated vision systems, i.e., for which painstaking procedures have been followed in order to estimate the values of the systems internal parameters. Unfortunately, the calibration process is a very slow and difficult procedure, often of inadequate accuracy and requiring systems to be taken off-line for large amounts of time, thus leading to increased costs. Moreover there is no guarantee that the estimated parameters will not change, for instance due to mechanical or environmental reasons, or if the camera uses a zoom mechanism. Uncalibrated computer vision dispenses with the whole calibration procedure, extracting all the information it needs from the images themselves. Hence, it allows for greater versatility since no assumptions about the camera setup are made, and greater robustness since one possible source of error, i.e., the calibration procedure, is eliminated. Especially the field of underwater applications of computer vision where thermal and mechanical strains on the camera are the norm, along with a usually unknown and highly unstructured environment, badly illuminated scenes and noisy images, provides with an environment where the use of Uncalibrated computer vision techniques could prove very beneficial. This paper will demonstrate early results of the application of Uncalibrated computer vision techniques in the underwater environment. The robustness and versatility of the techniques will be demonstrated through synthetic data and real underwater sequences.

Original languageEnglish
Pages (from-to)11/1-11/6
JournalIEE Colloquium (Digest)
Issue number217
Publication statusPublished - 1998

Fingerprint

Computer vision
Cameras
Calibration
Costs

Cite this

Plakas, K. ; Trucco, E. / Uncalibrated computer vision techniques in the underwater environment. In: IEE Colloquium (Digest). 1998 ; No. 217. pp. 11/1-11/6.
@article{26d4130bc5fd43b9a1209af86a358cfa,
title = "Uncalibrated computer vision techniques in the underwater environment",
abstract = "Uncalibrated computer vision is a relatively new but fast growing area of computer vision research. Until recently, computer vision research has focused mainly on calibrated vision systems, i.e., for which painstaking procedures have been followed in order to estimate the values of the systems internal parameters. Unfortunately, the calibration process is a very slow and difficult procedure, often of inadequate accuracy and requiring systems to be taken off-line for large amounts of time, thus leading to increased costs. Moreover there is no guarantee that the estimated parameters will not change, for instance due to mechanical or environmental reasons, or if the camera uses a zoom mechanism. Uncalibrated computer vision dispenses with the whole calibration procedure, extracting all the information it needs from the images themselves. Hence, it allows for greater versatility since no assumptions about the camera setup are made, and greater robustness since one possible source of error, i.e., the calibration procedure, is eliminated. Especially the field of underwater applications of computer vision where thermal and mechanical strains on the camera are the norm, along with a usually unknown and highly unstructured environment, badly illuminated scenes and noisy images, provides with an environment where the use of Uncalibrated computer vision techniques could prove very beneficial. This paper will demonstrate early results of the application of Uncalibrated computer vision techniques in the underwater environment. The robustness and versatility of the techniques will be demonstrated through synthetic data and real underwater sequences.",
author = "K. Plakas and E. Trucco",
year = "1998",
language = "English",
pages = "11/1--11/6",
journal = "IEE Colloquium (Digest)",
issn = "0963-3308",
publisher = "Institute of Electrical Engineers",
number = "217",

}

Uncalibrated computer vision techniques in the underwater environment. / Plakas, K.; Trucco, E.

In: IEE Colloquium (Digest), No. 217, 1998, p. 11/1-11/6.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Uncalibrated computer vision techniques in the underwater environment

AU - Plakas, K.

AU - Trucco, E.

PY - 1998

Y1 - 1998

N2 - Uncalibrated computer vision is a relatively new but fast growing area of computer vision research. Until recently, computer vision research has focused mainly on calibrated vision systems, i.e., for which painstaking procedures have been followed in order to estimate the values of the systems internal parameters. Unfortunately, the calibration process is a very slow and difficult procedure, often of inadequate accuracy and requiring systems to be taken off-line for large amounts of time, thus leading to increased costs. Moreover there is no guarantee that the estimated parameters will not change, for instance due to mechanical or environmental reasons, or if the camera uses a zoom mechanism. Uncalibrated computer vision dispenses with the whole calibration procedure, extracting all the information it needs from the images themselves. Hence, it allows for greater versatility since no assumptions about the camera setup are made, and greater robustness since one possible source of error, i.e., the calibration procedure, is eliminated. Especially the field of underwater applications of computer vision where thermal and mechanical strains on the camera are the norm, along with a usually unknown and highly unstructured environment, badly illuminated scenes and noisy images, provides with an environment where the use of Uncalibrated computer vision techniques could prove very beneficial. This paper will demonstrate early results of the application of Uncalibrated computer vision techniques in the underwater environment. The robustness and versatility of the techniques will be demonstrated through synthetic data and real underwater sequences.

AB - Uncalibrated computer vision is a relatively new but fast growing area of computer vision research. Until recently, computer vision research has focused mainly on calibrated vision systems, i.e., for which painstaking procedures have been followed in order to estimate the values of the systems internal parameters. Unfortunately, the calibration process is a very slow and difficult procedure, often of inadequate accuracy and requiring systems to be taken off-line for large amounts of time, thus leading to increased costs. Moreover there is no guarantee that the estimated parameters will not change, for instance due to mechanical or environmental reasons, or if the camera uses a zoom mechanism. Uncalibrated computer vision dispenses with the whole calibration procedure, extracting all the information it needs from the images themselves. Hence, it allows for greater versatility since no assumptions about the camera setup are made, and greater robustness since one possible source of error, i.e., the calibration procedure, is eliminated. Especially the field of underwater applications of computer vision where thermal and mechanical strains on the camera are the norm, along with a usually unknown and highly unstructured environment, badly illuminated scenes and noisy images, provides with an environment where the use of Uncalibrated computer vision techniques could prove very beneficial. This paper will demonstrate early results of the application of Uncalibrated computer vision techniques in the underwater environment. The robustness and versatility of the techniques will be demonstrated through synthetic data and real underwater sequences.

UR - http://www.scopus.com/inward/record.url?scp=0031675267&partnerID=8YFLogxK

M3 - Article

SP - 11/1-11/6

JO - IEE Colloquium (Digest)

JF - IEE Colloquium (Digest)

SN - 0963-3308

IS - 217

ER -