Automated Detection of Hillforts in Remote Sensing Imagery With Deep Multimodal Segmentation.

Recent 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...

Descripción completa

Detalles Bibliográficos
Publicado en:Archaeological Prospection Vol. 32; no. 2; pp. 297 - 312
Autores principales: Canedo, Daniel, Fonte, João, Dias, Rita, do Pereiro, Tiago, Gonçalves‐Seco, Luís, Vázquez, Marta, Georgieva, Petia, Neves, António J. R.
Formato: Artículo
Publicado: Wiley-Blackwell Apr2025
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=185659949&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 185659949
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        10752196
        58D
      jtl: Archaeological Prospection
      issn: 10752196
      maglogo: Y
    pubinfo:
      dt: Apr2025
      vid: 32
      iid: 2
      pid: 480
      pub: Wiley-Blackwell
    artinfo:
      ui:
        185659949
        10.1002/arp.1958
      ppf: 297
      ppct: 15
      formats:
      tig:
        atl: Automated Detection of Hillforts in Remote Sensing Imagery With Deep Multimodal Segmentation.
      aug:
        au:
          Canedo, Daniel
          Fonte, João
          Dias, Rita
          do Pereiro, Tiago
          Gonçalves‐Seco, Luís
          Vázquez, Marta
          Georgieva, Petia
          Neves, António J. R.
        affil:
          IEETA/DETI, University of Aveiro, Aveiro, Portugal
          Department of Archaeology and History, University of Exeter, Exeter, UK
          ERA Arqueologia, Calçada de Santa Catarina, Cruz Quebrada, Portugal
          Centre for the Humanities (CHAM), Faculdade de Ciências Sociais e Humanas, Universidade NOVA de Lisboa, Lisboa, Portugal
          ICArEHB, Campus de Gambelas, Universidade do Algarve, Faro, Portugal
          UMAIA, University of Maia, Maia, Portugal
          INESC TEC–Institute for Systems and Computer Engineering, Technology and Science, University of Porto, Porto, Portugal
          N2i, Polytechnic Institute of Maia, Maia, Portugal
          Instituto de Telecomunicações, Universidade de Aveiro, Aveiro, Portugal
      su:
        Computer vision
        Artificial intelligence
        Remote sensing
        Computer performance
        Computer systems
      sug:
        subj:
          Computer vision
          Artificial intelligence
          Remote sensing
          Computer performance
          Computer systems
      keyword:
        computer vision
        hillforts
        LiDAR
        multimodal semantic segmentation
        orthoimagery
        transformer
      ab: Recent 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 F1 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.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N