|   | 
Détails
   web
Enregistrements
Auteur (up) Villon, S.; Chaumont, M.; Subsol, G.; Villeger, S.; Claverie, T.; Mouillot, D.
Titre Coral Reef Fish Detection and Recognition in Underwater Videos by Supervised Machine Learning: Comparison Between Deep Learning and HOG plus SVM Methods Type Chapitre de livre
Année 2016 Publication Revue Abrégée
Volume Numéro Pages 160-171
Mots-Clés model; neural-networks; object detection; remote-sensing images
Résumé In this paper, we present two supervised machine learning methods to automatically detect and recognize coral reef fishes in underwater HD videos. The first method relies on a traditional two-step approach: extraction of HOG features and use of a SVM classifier. The second method is based on Deep Learning. We compare the results of the two methods on real data and discuss their strengths and weaknesses.
Adresse
Auteur institutionnel Thèse
Editeur Springer Int Publishing Ag Lieu de Publication Cham Éditeur BlancTalon, J.; Distante, C.; Philips, W.; Popescu, D.; Scheunders, P.
Langue English Langue du Résumé Titre Original
Éditeur de collection Titre de collection Titre de collection Abrégé Advanced Concepts for Intelligent Vision Systems, Acivs 2016
Volume de collection 10016 Numéro de collection Edition
ISSN ISBN 978-3-319-48680-2 978-3-319-48679-6 Médium
Région Expédition Conférence
Notes Approuvé pas de
Numéro d'Appel MARBEC @ alain.herve @ collection 2138
Lien permanent pour cet enregistrement
 

 
Auteur (up) Villon, S.; Mouillot, D.; Chaumont, M.; Darling, E.S.; Subsol, G.; Claverie, T.; Villeger, S.
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 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