bascule de visibilité Search & Display Options

Tout Sélectionner    Désélectionner
 |   | 
Détails
   print
  Enregistrement Liens
Auteur Villon, S.; Mouillot, D.; Chaumont, M.; Darling, E.S.; Subsol, G.; Claverie, T.; Villeger, S. doi  openurl
  Titre A Deep learning method for accurate and fast identification of coral reef fishes in underwater images Type Article scientifique
  Année 2018 Publication Revue Abrégée Ecol. Inform.  
  Volume 48 Numéro Pages 238-244  
  Mots-Clés Automated identification; Convolutional neural network; density; Machine learning; Marine fishes; neural-networks; system; temperate; Underwater pictures; video stations; visual census; vulnerability  
  Résumé Identifying and counting fish individuals on photos and videos is a crucial task to cost-effectively monitor marine biodiversity, yet it remains difficult and time-consuming. In this paper, we present a method to assist the identification of fish species on underwater images, and we compare our model performances to human ability in terms of speed and accuracy. We first tested the performance of a convolutional neural network (CNN) trained with different photographic databases while accounting for different post-processing decision rules to identify 20 fish species. Finally, we compared the performance of species identification of our best CNN model with that of humans on a test database of 1197 fish images representing nine species. The best CNN was the one trained with 900,000 images including (i) whole fish bodies, (ii) partial fish bodies and (iii) the environment (e.g. reef bottom or water). The rate of correct identification was 94.9%, greater than the rate of correct identification by humans (89.3%). The CNN was also able to identify fish individuals partially hidden behind corals or behind other fish and was more effective than humans to identify fish on smallest or blurry images while humans were better to identify fish individuals in unusual positions (e.g. twisted body). On average, each identification by our best CNN using a common hardware took 0.06 s. Deep Learning methods can thus perform efficient fish identification on underwater images and offer promises to build-up new video-based protocols for monitoring fish biodiversity cheaply and effectively.  
  Adresse  
  Auteur institutionnel Thèse  
  Editeur Lieu de Publication Éditeur  
  Langue English Langue du Résumé Titre Original  
  Éditeur de collection Titre de collection Titre de collection Abrégé  
  Volume de collection (down) Numéro de collection Edition  
  ISSN 1574-9541 ISBN Médium  
  Région Expédition Conférence  
  Notes Approuvé pas de  
  Numéro d'Appel MARBEC @ isabelle.vidal-ayouba @ collection 2475  
Lien permanent pour cet enregistrement
Tout Sélectionner    Désélectionner
 |   | 
Détails
   print

Save Citations:
Export Records: