Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN

Schoening T, Bergmann M, Purser A, Dannheim J, Gutt J, Nattkemper TW. Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN. PLoS ONE . 2012;7(6): e38179. Megafauna play an important role in benthic ecosystem function and are sensitive...

Full description

Bibliographic Details
Published in:PLoS ONE
Main Authors: Schoening, Timm, Bergmann, Melanie, Purser, Autun, Dannheim, Jennifer, Gutt, Julian, Nattkemper, Tim Wilhelm
Format: Article in Journal/Newspaper
Language:English
Published: Public Library of Science (PLoS) 2012
Subjects:
Online Access:https://nbn-resolving.org/urn:nbn:de:0070-pub-24944580
https://pub.uni-bielefeld.de/record/2494458
https://pub.uni-bielefeld.de/download/2494458/2509590
id ftubbiepub:oai:pub.uni-bielefeld.de:2494458
record_format openpolar
spelling ftubbiepub:oai:pub.uni-bielefeld.de:2494458 2023-05-15T14:55:39+02:00 Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN Schoening, Timm Bergmann, Melanie Purser, Autun Dannheim, Jennifer Gutt, Julian Nattkemper, Tim Wilhelm 2012 https://nbn-resolving.org/urn:nbn:de:0070-pub-24944580 https://pub.uni-bielefeld.de/record/2494458 https://pub.uni-bielefeld.de/download/2494458/2509590 eng eng Public Library of Science (PLoS) info:eu-repo/semantics/altIdentifier/doi/10.1371/journal.pone.0038179 info:eu-repo/semantics/altIdentifier/issn/1932-6203 info:eu-repo/semantics/altIdentifier/wos/000305343900020 info:eu-repo/semantics/altIdentifier/pmid/22719868 https://nbn-resolving.org/urn:nbn:de:0070-pub-24944580 https://pub.uni-bielefeld.de/record/2494458 https://pub.uni-bielefeld.de/download/2494458/2509590 info:eu-repo/semantics/openAccess https://rightsstatements.org/vocab/InC/1.0/ ddc:570 http://purl.org/coar/resource_type/c_6501 info:eu-repo/semantics/article doc-type:article text 2012 ftubbiepub https://doi.org/10.1371/journal.pone.0038179 2022-02-08T22:32:37Z Schoening T, Bergmann M, Purser A, Dannheim J, Gutt J, Nattkemper TW. Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN. PLoS ONE . 2012;7(6): e38179. Megafauna play an important role in benthic ecosystem function and are sensitive indicators of environmental change. Non-invasive monitoring of benthic communities can be accomplished by seafloor imaging. However, manual quantification of megafauna in images is labor-intensive and therefore, this organism size class is often neglected in ecosystem studies. Automated image analysis has been proposed as a possible approach to such analysis, but the heterogeneity of megafaunal communities poses a non-trivial challenge for such automated techniques. Here, the potential of a generalized object detection architecture, referred to as iSIS (intelligent Screening of underwater Image Sequences), for the quantification of a heterogenous group of megafauna taxa is investigated. The iSIS system is tuned for a particular image sequence (i.e. a transect) using a small subset of the images, in which megafauna taxa positions were previously marked by an expert. To investigate the potential of iSIS and compare its results with those obtained from human experts, a group of eight different taxa from one camera transect of seafloor images taken at the Arctic deep-sea observatory HAUSGARTEN is used. The results show that inter- and intra-observer agreements of human experts exhibit considerable variation between the species, with a similar degree of variation apparent in the automatically derived results obtained by iSIS. Whilst some taxa (e. g. Bathycrinus stalks, Kolga hyalina, small white sea anemone) were well detected by iSIS (i. e. overall Sensitivity: 87%, overall Positive Predictive Value: 67%), some taxa such as the small sea cucumber Elpidia heckeri remain challenging, for both human observers and iSIS. Article in Journal/Newspaper Arctic White Sea PUB - Publications at Bielefeld University Arctic White Sea PLoS ONE 7 6 e38179
institution Open Polar
collection PUB - Publications at Bielefeld University
op_collection_id ftubbiepub
language English
topic ddc:570
spellingShingle ddc:570
Schoening, Timm
Bergmann, Melanie
Purser, Autun
Dannheim, Jennifer
Gutt, Julian
Nattkemper, Tim Wilhelm
Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN
topic_facet ddc:570
description Schoening T, Bergmann M, Purser A, Dannheim J, Gutt J, Nattkemper TW. Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN. PLoS ONE . 2012;7(6): e38179. Megafauna play an important role in benthic ecosystem function and are sensitive indicators of environmental change. Non-invasive monitoring of benthic communities can be accomplished by seafloor imaging. However, manual quantification of megafauna in images is labor-intensive and therefore, this organism size class is often neglected in ecosystem studies. Automated image analysis has been proposed as a possible approach to such analysis, but the heterogeneity of megafaunal communities poses a non-trivial challenge for such automated techniques. Here, the potential of a generalized object detection architecture, referred to as iSIS (intelligent Screening of underwater Image Sequences), for the quantification of a heterogenous group of megafauna taxa is investigated. The iSIS system is tuned for a particular image sequence (i.e. a transect) using a small subset of the images, in which megafauna taxa positions were previously marked by an expert. To investigate the potential of iSIS and compare its results with those obtained from human experts, a group of eight different taxa from one camera transect of seafloor images taken at the Arctic deep-sea observatory HAUSGARTEN is used. The results show that inter- and intra-observer agreements of human experts exhibit considerable variation between the species, with a similar degree of variation apparent in the automatically derived results obtained by iSIS. Whilst some taxa (e. g. Bathycrinus stalks, Kolga hyalina, small white sea anemone) were well detected by iSIS (i. e. overall Sensitivity: 87%, overall Positive Predictive Value: 67%), some taxa such as the small sea cucumber Elpidia heckeri remain challenging, for both human observers and iSIS.
format Article in Journal/Newspaper
author Schoening, Timm
Bergmann, Melanie
Purser, Autun
Dannheim, Jennifer
Gutt, Julian
Nattkemper, Tim Wilhelm
author_facet Schoening, Timm
Bergmann, Melanie
Purser, Autun
Dannheim, Jennifer
Gutt, Julian
Nattkemper, Tim Wilhelm
author_sort Schoening, Timm
title Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN
title_short Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN
title_full Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN
title_fullStr Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN
title_full_unstemmed Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN
title_sort semi-automated image analysis for the assessment of megafaunal densities at the arctic deep-sea observatory hausgarten
publisher Public Library of Science (PLoS)
publishDate 2012
url https://nbn-resolving.org/urn:nbn:de:0070-pub-24944580
https://pub.uni-bielefeld.de/record/2494458
https://pub.uni-bielefeld.de/download/2494458/2509590
geographic Arctic
White Sea
geographic_facet Arctic
White Sea
genre Arctic
White Sea
genre_facet Arctic
White Sea
op_relation info:eu-repo/semantics/altIdentifier/doi/10.1371/journal.pone.0038179
info:eu-repo/semantics/altIdentifier/issn/1932-6203
info:eu-repo/semantics/altIdentifier/wos/000305343900020
info:eu-repo/semantics/altIdentifier/pmid/22719868
https://nbn-resolving.org/urn:nbn:de:0070-pub-24944580
https://pub.uni-bielefeld.de/record/2494458
https://pub.uni-bielefeld.de/download/2494458/2509590
op_rights info:eu-repo/semantics/openAccess
https://rightsstatements.org/vocab/InC/1.0/
op_doi https://doi.org/10.1371/journal.pone.0038179
container_title PLoS ONE
container_volume 7
container_issue 6
container_start_page e38179
_version_ 1766327676874784768