Repository logo
 
Publication

Quantifying Marine Macro Litter Abundance on a Sandy Beach Using Unmanned Aerial Systems and Object-Oriented Machine Learning Methods

2020-08-12Journal article Open access
Simple item page
datacite.subject.fosCiências Naturais::Ciências da Terra e do Ambiente
datacite.subject.sdg07:Energias Renováveis e Acessíveis
datacite.subject.sdg09:Indústria, Inovação e Infraestruturas
datacite.subject.sdg11:Cidades e Comunidades Sustentáveis
dc.contributor.authorGonçalves, Gil
dc.contributor.authorAndriolo, Umberto
dc.contributor.authorGonçalves, Luisa
dc.contributor.authorSobral, Paula
dc.contributor.authorBessa, Filipa
dc.date.accessioned2025-09-03T12:07:22Z
dc.date.available2025-09-03T12:07:22Z
dc.date.issued2020-08-12
dc.description.abstractUnmanned aerial systems (UASs) have recently been proven to be valuable remote sensing tools for detecting marine macro litter (MML), with the potential of supporting pollution monitoring programs on coasts. Very low altitude images, acquired with a low-cost RGB camera onboard a UAS on a sandy beach, were used to characterize the abundance of stranded macro litter. We developed an object-oriented classification strategy for automatically identifying the marine macro litter items on a UAS-based orthomosaic. A comparison is presented among three automated object-oriented machine learning (OOML) techniques, namely random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). Overall, the detection was satisfactory for the three techniques, with mean F-scores of 65% for KNN, 68% for SVM, and 72% for RF. A comparison with manual detection showed that the RF technique was the most accurate OOML macro litter detector, as it returned the best overall detection quality (F-score) with the lowest number of false positives. Because the number of tuning parameters varied among the three automated machine learning techniques and considering that the three generated abundance maps correlated similarly with the abundance map produced manually, the simplest KNN classifier was preferred to the more complex RF. This work contributes to advances in remote sensing marine litter surveys on coasts, optimizing the automated detection on UAS-derived orthomosaics. MML abundance maps, produced by UAS surveys, assist coastal managers and authorities through environmental pollution monitoring programs. In addition, they contribute to search and evaluation of the mitigation measures and improve clean-up operations on coastal environments.eng
dc.description.sponsorshipThis work was supported by the Portuguese Foundation for Science and Technology (FCT) and by the European Regional Development Fund (FEDER) through COMPETE 2020, Operational Program for Competitiveness and Internationalization (POCI) in the framework of UIDB 00308/2020 and the research project UAS4Litter (PTDC/EAM-REM/30324/2017). The work of F.B. was supported by the University of Coimbra through contract IT057-18-7252. F.B. and P.S. acknowledge FCT through the strategic project UIDB/04292/2020 granted to MARE.
dc.identifier.citationGonçalves, G., Andriolo, U., Gonçalves, L., Sobral, P., & Bessa, F. (2020). Quantifying Marine Macro Litter Abundance on a Sandy Beach Using Unmanned Aerial Systems and Object-Oriented Machine Learning Methods. Remote Sensing, 12(16), 2599. https://doi.org/10.3390/rs12162599.
dc.identifier.doi10.3390/rs12162599
dc.identifier.eissn2072-4292
dc.identifier.urihttp://hdl.handle.net/10400.8/13966
dc.language.isoeng
dc.peerreviewedyes
dc.publisherMDPI
dc.relationInstitute for Systems Engineering and Computers at Coimbra - INESC Coimbra
dc.relationLow-cost Unmanned Aerial Systems (UASs) for marine litter coastal mapping
dc.relation.hasversionhttps://www.mdpi.com/2072-4292/12/16/2599
dc.relation.ispartofRemote Sensing
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectdrone
dc.subjectanthropogenic debris
dc.subjectOBIA
dc.subjectrandom forest
dc.subjectsupport vector machine
dc.subjectk-nearest neighbor
dc.titleQuantifying Marine Macro Litter Abundance on a Sandy Beach Using Unmanned Aerial Systems and Object-Oriented Machine Learning Methodseng
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleInstitute for Systems Engineering and Computers at Coimbra - INESC Coimbra
oaire.awardTitleLow-cost Unmanned Aerial Systems (UASs) for marine litter coastal mapping
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00308%2F2020/PT
oaire.awardURIhttp://hdl.handle.net/10400.8/13965
oaire.citation.endPage19
oaire.citation.issue16
oaire.citation.startPage1
oaire.citation.titleRemote Sensing
oaire.citation.volume12
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStreamConcurso para Financiamento de Projetos de Investigação Científica e Desenvolvimento Tecnológico em Todos os Domínios Científicos - 2017
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameGonçalves
person.givenNameLuisa
person.identifier.ciencia-id9116-82A0-3060
person.identifier.orcid0000-0002-6265-8903
person.identifier.ridU-1298-2017
person.identifier.scopus-author-id35145815700
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublication1ba44699-bdda-4e01-97ec-c02fe603afc5
relation.isAuthorOfPublication.latestForDiscovery1ba44699-bdda-4e01-97ec-c02fe603afc5
relation.isProjectOfPublication254d9223-2e3b-4754-bae9-c98986d80921
relation.isProjectOfPublication0492d5f0-5177-460d-addd-93b12cac4cf3
relation.isProjectOfPublication.latestForDiscovery254d9223-2e3b-4754-bae9-c98986d80921

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Quantifying marine macro litter abundance on a sandy beach using unmanned aerial systems and object-oriented machine learning methods.pdf
Size:
5.19 MB
Format:
Adobe Portable Document Format
Description:
Unmanned aerial systems (UASs) have recently been proven to be valuable remote sensing tools for detecting marine macro litter (MML), with the potential of supporting pollution monitoring programs on coasts. Very low altitude images, acquired with a low-cost RGB camera onboard a UAS on a sandy beach, were used to characterize the abundance of stranded macro litter. We developed an object-oriented classification strategy for automatically identifying the marine macro litter items on a UAS-based orthomosaic. A comparison is presented among three automated object-oriented machine learning (OOML) techniques, namely random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). Overall, the detection was satisfactory for the three techniques, with mean F-scores of 65% for KNN, 68% for SVM, and 72% for RF. A comparison with manual detection showed that the RF technique was the most accurate OOML macro litter detector, as it returned the best overall detection quality (F-score) with the lowest number of false positives. Because the number of tuning parameters varied among the three automated machine learning techniques and considering that the three generated abundance maps correlated similarly with the abundance map produced manually, the simplest KNN classifier was preferred to the more complex RF. This work contributes to advances in remote sensing marine litter surveys on coasts, optimizing the automated detection on UAS-derived orthomosaics. MML abundance maps, produced by UAS surveys, assist coastal managers and authorities through environmental pollution monitoring programs. In addition, they contribute to search and evaluation of the mitigation measures and improve clean-up operations on coastal environments.
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.32 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

INESCC-DL - Artigos em Revistas Internacionais
ESTG - Artigos em revistas internacionais