Leveraging social media and deep learning to detect rare megafauna in video surveys - Université de la Nouvelle-Calédonie Accéder directement au contenu
Article Dans Une Revue Conservation Biology Année : 2022

Leveraging social media and deep learning to detect rare megafauna in video surveys

Résumé

Deep learning has become a key tool for the automated monitoring of animal populations with video surveys. However, obtaining large numbers of images to train such models is a major challenge for rare and elusive species because field video surveys provide few sightings. We designed a method that takes advantage of videos accumulated on social media for training deep-learning models to detect rare megafauna species in the field. We trained convolutional neural networks (CNNs) with social media images and tested them on images collected from field surveys. We applied our method to aerial video surveys of dugongs (Dugong dugon) in New Caledonia (southwestern Pacific). CNNs trained with 1303 social media images yielded 25% false positives and 38% false negatives when tested on independent field video surveys. Incorporating a small number of images from New Caledonia (equivalent to 12% of social media images) in the training data set resulted in a nearly 50% decrease in false negatives. Our results highlight how and the extent to which images collected on social media can offer a solid basis for training deep-learning models for rare megafauna detection and that the incorporation of a few images from the study site further boosts detection accuracy. Our method provides a new generation of deep-learning models that can be used to rapidly and accurately process field video surveys for the monitoring of rare megafauna.
Fichier principal
Vignette du fichier
Conservation Biology - 2021 - Mannocci - Leveraging social media and deep learning to detect rare megafauna in video.pdf (1.52 Mo) Télécharger le fichier
Origine : Publication financée par une institution

Dates et versions

hal-03405365 , version 1 (15-12-2021)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

Citer

Laura Mannocci, Sébastien Villon, Marc Chaumont, Nacim Guellati, Nicolas Mouquet, et al.. Leveraging social media and deep learning to detect rare megafauna in video surveys. Conservation Biology, 2022, 36 (1), pp.e13798. ⟨10.1111/cobi.13798⟩. ⟨hal-03405365⟩
78 Consultations
61 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More