RECOMIA - RECOMMENDATIONS FOR MARINE IMAGE ANNOTATION: LESSONS LEARNED AND FUTURE DIRECTIONS
Marine imaging is transforming into a sensor technology applied for high throughput sampling. In the context of habitat mapping, imaging establishes thereby an important bridge technology regarding the spatial resolution and information content between physical sampling gear (e.g. box corer, multi c...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2016-04-01
|
Series: | Frontiers in Marine Science |
Subjects: | |
Online Access: | http://journal.frontiersin.org/Journal/10.3389/fmars.2016.00059/full |
id |
doaj-e2c85f055be84c8ca1591f074f2b9666 |
---|---|
record_format |
Article |
spelling |
doaj-e2c85f055be84c8ca1591f074f2b96662020-11-25T01:57:11ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452016-04-01310.3389/fmars.2016.00059191430RECOMIA - RECOMMENDATIONS FOR MARINE IMAGE ANNOTATION: LESSONS LEARNED AND FUTURE DIRECTIONSTimm eSchoening0Jonas eOsterloff1Tim Wilhelm Nattkemper2GEOMAR Helmholtz Centre for Ocean ResearchBielefeld UniversityBielefeld UniversityMarine imaging is transforming into a sensor technology applied for high throughput sampling. In the context of habitat mapping, imaging establishes thereby an important bridge technology regarding the spatial resolution and information content between physical sampling gear (e.g. box corer, multi corer) on the one end and hydro-acoustic sensors on the other end of the spectrum of sampling methods. In contrast to other scientific imaging domains, such as digital pathology, there are no protocols and reports available that guide users (often referred to as observers) in the non-trivial process of assigning semantic categories to whole images, regions or objects of interest, which is referred to as annotation. These protocols are crucial to facilitate image analysis as a robust scientific method.In this article we will review the past observations in manual Marine Image Annotations (MIA) and provide a) a guideline for collecting manual annotations, b) definitions for annotation quality and c) a statistical framework to analyze the performance of human expert annotations and to compare those to computational approaches.http://journal.frontiersin.org/Journal/10.3389/fmars.2016.00059/fullEnvironmental Monitoringimage annotationenvironmental scienceshabitat mappingUnderwater image analysisMarine Imaging |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Timm eSchoening Jonas eOsterloff Tim Wilhelm Nattkemper |
spellingShingle |
Timm eSchoening Jonas eOsterloff Tim Wilhelm Nattkemper RECOMIA - RECOMMENDATIONS FOR MARINE IMAGE ANNOTATION: LESSONS LEARNED AND FUTURE DIRECTIONS Frontiers in Marine Science Environmental Monitoring image annotation environmental sciences habitat mapping Underwater image analysis Marine Imaging |
author_facet |
Timm eSchoening Jonas eOsterloff Tim Wilhelm Nattkemper |
author_sort |
Timm eSchoening |
title |
RECOMIA - RECOMMENDATIONS FOR MARINE IMAGE ANNOTATION: LESSONS LEARNED AND FUTURE DIRECTIONS |
title_short |
RECOMIA - RECOMMENDATIONS FOR MARINE IMAGE ANNOTATION: LESSONS LEARNED AND FUTURE DIRECTIONS |
title_full |
RECOMIA - RECOMMENDATIONS FOR MARINE IMAGE ANNOTATION: LESSONS LEARNED AND FUTURE DIRECTIONS |
title_fullStr |
RECOMIA - RECOMMENDATIONS FOR MARINE IMAGE ANNOTATION: LESSONS LEARNED AND FUTURE DIRECTIONS |
title_full_unstemmed |
RECOMIA - RECOMMENDATIONS FOR MARINE IMAGE ANNOTATION: LESSONS LEARNED AND FUTURE DIRECTIONS |
title_sort |
recomia - recommendations for marine image annotation: lessons learned and future directions |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Marine Science |
issn |
2296-7745 |
publishDate |
2016-04-01 |
description |
Marine imaging is transforming into a sensor technology applied for high throughput sampling. In the context of habitat mapping, imaging establishes thereby an important bridge technology regarding the spatial resolution and information content between physical sampling gear (e.g. box corer, multi corer) on the one end and hydro-acoustic sensors on the other end of the spectrum of sampling methods. In contrast to other scientific imaging domains, such as digital pathology, there are no protocols and reports available that guide users (often referred to as observers) in the non-trivial process of assigning semantic categories to whole images, regions or objects of interest, which is referred to as annotation. These protocols are crucial to facilitate image analysis as a robust scientific method.In this article we will review the past observations in manual Marine Image Annotations (MIA) and provide a) a guideline for collecting manual annotations, b) definitions for annotation quality and c) a statistical framework to analyze the performance of human expert annotations and to compare those to computational approaches. |
topic |
Environmental Monitoring image annotation environmental sciences habitat mapping Underwater image analysis Marine Imaging |
url |
http://journal.frontiersin.org/Journal/10.3389/fmars.2016.00059/full |
work_keys_str_mv |
AT timmeschoening recomiarecommendationsformarineimageannotationlessonslearnedandfuturedirections AT jonaseosterloff recomiarecommendationsformarineimageannotationlessonslearnedandfuturedirections AT timwilhelmnattkemper recomiarecommendationsformarineimageannotationlessonslearnedandfuturedirections |
_version_ |
1724975900325314560 |