Whale counting in satellite and aerial images with deep learning
Metadatos
Mostrar el registro completo del ítemAutor
Guirado, Emilio; Tabik, Siham; Rivas, Marga; Alcaraz Segura, Domingo; Herrera Triguero, FranciscoEditorial
Springer Nature
Fecha
2019-10-03Referencia bibliográfica
Guirado, E., Tabik, S., Rivas, M. L., Alcaraz-Segura, D., & Herrera, F. (2019). Whale counting in satellite and aerial images with deep learning. Scientific reports, 9(1), 1-12.
Patrocinador
S.T. was supported by the Ramón y Cajal Programme of the Spanish government (RYC-2015-18136). S.T., E.G., and F.H. were supported by the Spanish Ministry of Science under the project TIN2017-89517-P. D. A-S. received support from European LIFE Project ADAPTAMED LIFE14 CCA/ES/000612, and from ERDF and Andalusian Government under the project GLOCHARID. D.A.-S. received support from NASA Work Programme on Group on Earth Observations - Biodiversity Observation Network (GEOBON) under grant 80NSSC18K0446, from project ECOPOTENTIAL, funded by European Union Horizon 2020 Research and Innovation Programme under grant agreement No. 641762, and from the Spanish Ministry of Science under project CGL2014-61610-EXP and grant JC2015-00316. M.R. received support from International mobility grant for prestigious researchers by (CEIMAR) International Campus of Excellence of the Sea.Resumen
Despite their interest and threat status, the number of whales in world’s oceans remains highly
uncertain. Whales detection is normally carried out from costly sighting surveys, acoustic surveys or
through high-resolution images. Since deep convolutional neural networks (CNNs) are achieving great
performance in several computer vision tasks, here we propose a robust and generalizable CNN-based
system for automatically detecting and counting whales in satellite and aerial images based on open
data and tools. In particular, we designed a two-step whale counting approach, where the first CNN
finds the input images with whale presence, and the second CNN locates and counts each whale in those
images. A test of the system on Google Earth images in ten global whale-watching hotspots achieved a
performance (F1-measure) of 81% in detecting and 94% in counting whales. Combining these two steps
increased accuracy by 36% compared to a baseline detection model alone. Applying this cost-effective
method worldwide could contribute to the assessment of whale populations to guide conservation
actions. Free and global access to high-resolution imagery for conservation purposes would boost this
process.