Gray whale detection in satellite imagery using deep learning

Green, Katherine M. ORCID: https://orcid.org/0000-0003-4664-3354; Virdee, Mala K.; Cubaynes, Hannah C. ORCID: https://orcid.org/0000-0002-9497-154X; Aviles-Rivero, Angelica I.; Fretwell, Peter T. ORCID: https://orcid.org/0000-0002-1988-5844; Gray, Patrick C.; Johnston, David W.; Schönlieb, Carola-Bibiane; Torres, Leigh G.; Jackson, Jennifer A. ORCID: https://orcid.org/0000-0003-4158-1924. 2023 Gray whale detection in satellite imagery using deep learning. Remote Sensing for Ecology and Conservation, 9 (6). 829-840. 10.1002/rse2.352

Before downloading, please read NORA policies.

Preview

Text (Open Access)
© 2023 The Authors. Remote Sensing in Ecology and Conservation published by John Wiley & Sons Ltd on behalf of Zoological Society of London. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
Remote Sens Ecol Conserv - 2023 - Green - Gray whale detection in satellite imagery using deep learning.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial 4.0.
Download (1MB) | Preview

Official URL: https://zslpublications.onlinelibrary.wiley.com/do...

Abstract/Summary

The combination of very high resolution (VHR) satellite remote sensing imagery and deep learning via convolutional neural networks provides opportunities to improve global whale population surveys through increasing efficiency and spatial coverage. Many whale species are recovering from commercial whaling and face multiple anthropogenic threats. Regular, accurate population surveys are therefore of high importance for conservation efforts. In this study, a state-of-the-art object detection model (YOLOv5) was trained to detect gray whales (Eschrichtius robustus) in VHR satellite images, using training data derived from satellite images spanning different sea states in a key breeding habitat, as well as aerial imagery collected by unoccupied aircraft systems. Varying combinations of aerial and satellite imagery were incorporated into the training set. Mean average precision, whale precision, and recall ranged from 0.823 to 0.922, 0.800 to 0.939, and 0.843 to 0.889, respectively, across eight experiments. The results imply that including aerial imagery in the training data did not substantially impact model performance, and therefore, expansion of representative satellite datasets should be prioritized. The accuracy of the results on real-world data, along with short training times, indicates the potential of using this method to automate whale detection for population surveys.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	10.1002/rse2.352
ISSN:	2056-3485
Additional Keywords:	Gray whale, Eschrichtius robustus, remote sensing, VHR satellite imagery, CNN, machine learning
Date made live:	26 Jun 2023 17:25 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/533716

Item Type:

Publication - Article

Digital Object Identifier (DOI):

10.1002/rse2.352

ISSN:

2056-3485

Additional Keywords:

Gray whale, Eschrichtius robustus, remote sensing, VHR satellite imagery, CNN, machine learning

Date made live:

26 Jun 2023 17:25 +0 (UTC)

URI:

https://nora.nerc.ac.uk/id/eprint/533716