A Deep Learning-based Framework for the Detection of Schools of Herring in Echograms

Autor:	Rezvanifar, Alireza, Marques, Tunai Porto, Cote, Melissa, Albu, Alexandra Branzan, Slonimer, Alex, Tolhurst, Thomas, Ersahin, Kaan, Mudge, Todd, Gauthier, Stephane
Rok vydání:	2019
Předmět:	Computer Science - Machine Learning Computer Science - Computer Vision and Pattern Recognition Electrical Engineering and Systems Science - Image and Video Processing Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Tracking the abundance of underwater species is crucial for understanding the effects of climate change on marine ecosystems. Biologists typically monitor underwater sites with echosounders and visualize data as 2D images (echograms); they interpret these data manually or semi-automatically, which is time-consuming and prone to inconsistencies. This paper proposes a deep learning framework for the automatic detection of schools of herring from echograms. Experiments demonstrated that our approach outperforms a traditional machine learning algorithm using hand-crafted features. Our framework could easily be expanded to detect more species of interest to sustainable fisheries. Comment: Accepted to NeurIPS 2019 workshop on Tackling Climate Change with Machine Learning, Vancouver, Canada
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1910.08215 Zobrazit plný text záznamu View this record from Arxiv