Repository logo
 
Publication

Automated detection of hillforts in remote sensing imagery with deep multimodal segmentation

2024-09-16Journal article Open access
Simple item page
dc.contributor.authorCanedo, Daniel
dc.contributor.authorFonte, João
dc.contributor.authorDias, Rita
dc.contributor.authorPereiro, Tiago do
dc.contributor.authorGonçalves‐Seco, Luís
dc.contributor.authorVázquez, Marta
dc.contributor.authorGeorgieva, Petia
dc.contributor.authorNeves, António J. R.
dc.date.accessioned2024-10-23T09:17:08Z
dc.date.available2024-10-23T09:17:08Z
dc.date.issued2024-09-16
dc.description.abstractRecent advancements in remote sensing and artificial intelligence can potentially revolutionize the automated detection of archaeological sites. However, the challenging task of interpreting remote sensing imagery combined with the intricate shapes of archaeological sites can hinder the performance of computer vision systems. This work presents a computer vision system trained for efficient hillfort detection in remote sensing imagery. Equipped with an adapted multimodal semantic segmentation model, the system integrates LiDAR-derived LRM images and aerial orthoimages for feature fusion, generating a binary mask pinpointing detected hillforts. Post-processing includes margin and area filters to remove edge inferences and smaller anomalies. The resulting inferences are subjected to hard positive and negative mining, where expert archaeologists classify them to populate the training data with new samples for retraining the segmentation model. As the computer vision system is far more likely to encounter background images during its search, the training data are intentionally biased towards negative examples. This approach aims to reduce the number of false positives, typically seen when applying machine learning solutions to remote sensing imagery. Northwest Iberia experiments witnessed a drastic reduction in false positives, from 5678 to 40 after a single hard positive and negative mining iteration, yielding a 99.3% reduction, with a resulting F-1 score of 66%. In England experiments, the system achieved a 59% F1 score when fine-tuned and deployed countrywide. Its scalability to diverse archaeological sites is demonstrated by successfully detecting hillforts and other types of enclosures despite their typical complex and varied shapes. Future work will explore archaeological predictive modelling to identify regions with higher archaeological potential to focus the search, addressing processing time challenges.eng
dc.description.sponsorshipALG-01-0247-FEDER-070150; BG-RRP-2.004-0005; UIDP/50008/2020; UIDB/04666/2020
dc.identifier.doi10.1002/arp.1958
dc.identifier.eissn1099-0763
dc.identifier.issn1075-2196
dc.identifier.urihttp://hdl.handle.net/10400.1/26128
dc.language.isoeng
dc.peerreviewedyes
dc.publisherWiley
dc.relationInstituto de Telecomunicações
dc.relation.ispartofArchaeological Prospection
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectComputer vision
dc.subjectHillforts
dc.subjectLiDAR
dc.subjectMultimodal semantic segmentation
dc.subjectOrthoimagery
dc.subjectTransformer
dc.titleAutomated detection of hillforts in remote sensing imagery with deep multimodal segmentationeng
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleInstituto de Telecomunicações
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F50008%2F2020/PT
oaire.citation.endPage15
oaire.citation.startPage1
oaire.citation.titleArchaeological Prospection
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameDias
person.givenNameRita
person.identifier.ciencia-idF81F-AC62-BBC0
person.identifier.orcid0000-0003-2999-3133
person.identifier.scopus-author-id55458374800
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublication70a82b34-2ca4-494d-9789-6a4da9c97e27
relation.isAuthorOfPublication.latestForDiscovery70a82b34-2ca4-494d-9789-6a4da9c97e27
relation.isProjectOfPublicationfcbe2d59-4ccb-49ff-a429-eb61bca54349
relation.isProjectOfPublication.latestForDiscoveryfcbe2d59-4ccb-49ff-a429-eb61bca54349

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Archaeological Prospection - 2024 - Canedo - Automated Detection of Hillforts in Remote Sensing Imagery With Deep.pdf
Size:
13.65 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.46 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ICR2-Artigos (em revistas ou actas indexadas)