Real-time automatic sea-floor change detection from video

K. Lebart, E. Trucco, D. M. Lane

Research output: Contribution to journalArticle

Abstract

It is often the case that only sparse sequences of videos from scientific underwater surveys actually contain important information for the expert. A system automatically detecting those critical parts, particularly during the post-mission tape analysis, would alleviate the expert work load and improve data exploitation. In this paper, we present a novel set of algorithms to detect in real time significant context changes in benthic videos. The detectors presented rely on an unsupervised image classification scheme: the time changes in the image contents are analyzed in the feature space. The algorithms are explained in detail, and experimental results with real underwater images reported. Various issues related to the complexity of the problem of automatically analysing underwater videos are also discussed.

Original languageEnglish
Pages (from-to)1337-1343
Number of pages7
JournalOceans Conference Record
Volume2
Publication statusPublished - 2000
EventOceans 2000 - Providence, RI, USA
Duration: 11 Sep 200014 Sep 2000

Fingerprint

Image classification
Tapes
Detectors

Cite this

@article{76865fba6f3a47cf818fb67fcf0cacd3,
title = "Real-time automatic sea-floor change detection from video",
abstract = "It is often the case that only sparse sequences of videos from scientific underwater surveys actually contain important information for the expert. A system automatically detecting those critical parts, particularly during the post-mission tape analysis, would alleviate the expert work load and improve data exploitation. In this paper, we present a novel set of algorithms to detect in real time significant context changes in benthic videos. The detectors presented rely on an unsupervised image classification scheme: the time changes in the image contents are analyzed in the feature space. The algorithms are explained in detail, and experimental results with real underwater images reported. Various issues related to the complexity of the problem of automatically analysing underwater videos are also discussed.",
author = "K. Lebart and E. Trucco and Lane, {D. M.}",
year = "2000",
language = "English",
volume = "2",
pages = "1337--1343",
journal = "Oceans Conference Record",
issn = "0197-7385",
publisher = "IEEE",

}

Real-time automatic sea-floor change detection from video. / Lebart, K.; Trucco, E.; Lane, D. M.

In: Oceans Conference Record, Vol. 2, 2000, p. 1337-1343.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-time automatic sea-floor change detection from video

AU - Lebart, K.

AU - Trucco, E.

AU - Lane, D. M.

PY - 2000

Y1 - 2000

N2 - It is often the case that only sparse sequences of videos from scientific underwater surveys actually contain important information for the expert. A system automatically detecting those critical parts, particularly during the post-mission tape analysis, would alleviate the expert work load and improve data exploitation. In this paper, we present a novel set of algorithms to detect in real time significant context changes in benthic videos. The detectors presented rely on an unsupervised image classification scheme: the time changes in the image contents are analyzed in the feature space. The algorithms are explained in detail, and experimental results with real underwater images reported. Various issues related to the complexity of the problem of automatically analysing underwater videos are also discussed.

AB - It is often the case that only sparse sequences of videos from scientific underwater surveys actually contain important information for the expert. A system automatically detecting those critical parts, particularly during the post-mission tape analysis, would alleviate the expert work load and improve data exploitation. In this paper, we present a novel set of algorithms to detect in real time significant context changes in benthic videos. The detectors presented rely on an unsupervised image classification scheme: the time changes in the image contents are analyzed in the feature space. The algorithms are explained in detail, and experimental results with real underwater images reported. Various issues related to the complexity of the problem of automatically analysing underwater videos are also discussed.

UR - http://www.scopus.com/inward/record.url?scp=0034481857&partnerID=8YFLogxK

M3 - Article

VL - 2

SP - 1337

EP - 1343

JO - Oceans Conference Record

JF - Oceans Conference Record

SN - 0197-7385

ER -