Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloChallenges in the deep learning-based semantic segmentation of benthic communities from Ortho-images
Anno di pubblicazione2020
FormatoElettronico
Autore/iPavoni G.; Corsini M.; Pedersen N.; Petrovic V.; Cignoni P.
Affiliazioni autoriCNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; Center for Marine Biodiversity and Conservation, Scripps Institution of Oceanography, University of California, San Diego, USA; Institute for Telecommunications and Information Technology, University of California, San Diego, USA; CNR-ISTI, Pisa, Italy
Autori CNR e affiliazioni
  • GAIA PAVONI
  • PAOLO CIGNONI
  • MASSIMILIANO CORSINI
Lingua/e
  • inglese
AbstractSince the early days of the low-cost camera development, the collection of visual data has become a common practice in the underwater monitoring field. Nevertheless, video and image sequences are a trustworthy source of knowledge that remains partially untapped. Human-based image analysis is a time-consuming task that creates a bottleneck between data collection and extrapolation. Nowadays, the annotation of biologically meaningful information from imagery can be efficiently automated or accelerated by convolutional neural networks (CNN). Presenting our case studies, we offer an overview of the potentialities and difficulties of accurate automatic recognition and segmentation of benthic species. This paper focuses on the application of deep learning techniques to multi-view stereo reconstruction by-products (registered images, point clouds, ortho-projections), considering the proliferation of these techniques among the marine science community. Of particular importance is the need to semantically segment imagery in order to generate demographic data vital to understand and explore the changes happening within marine communities.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali16
RivistaApplied geomatics (Print)
Attiva dal 2009
Editore: Springer - Heidelberg
Paese di pubblicazione: Germania
Lingua: inglese
ISSN: 1866-9298
Titolo chiave: Applied geomatics (Print)
Titolo proprio: Applied geomatics. (Print)
Titolo abbreviato: Appl. geomat. (Print)
Numero volume della rivista-
Fascicolo della rivista-
DOI10.1007/s12518-020-00331-6
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85087897964)
  • ISI Web of Science (WOS) (Codice:000548105500001)
Parole chiaveUnderwater monitoring, Semantic segmentation, Automatic classification, Deep Learning, Coral reef surveys
Link (URL, URI)https://link.springer.com/article/10.1007/s12518-020-00331-6
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione02/07/2020
Note/Altre informazioniOnline first 14 July 2020
Strutture CNR
  • ISTI — Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"
Moduli/Attività/Sottoprogetti CNR-
Progetti Europei-
Allegati
Challenges in the deep learning-based semantic segmentation of benthic communities from Ortho-images (documento privato )
Descrizione: published version
Tipo documento: application/pdf