Cargando…

Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection

The vast amount of images generated by aerial imagery in the context of regular wildlife surveys nowadays require automatic processing tools. At the top of the mountain of different methods to automatically detect objects in images reigns deep learning’s object detection. The recent focus given to t...

Descripción completa

Detalles Bibliográficos
Autores principales: Moreni, Mael, Theau, Jerome, Foucher, Samuel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10124840/
https://www.ncbi.nlm.nih.gov/pubmed/37093866
http://dx.doi.org/10.1371/journal.pone.0284449
_version_ 1785029917933568000
author Moreni, Mael
Theau, Jerome
Foucher, Samuel
author_facet Moreni, Mael
Theau, Jerome
Foucher, Samuel
author_sort Moreni, Mael
collection PubMed
description The vast amount of images generated by aerial imagery in the context of regular wildlife surveys nowadays require automatic processing tools. At the top of the mountain of different methods to automatically detect objects in images reigns deep learning’s object detection. The recent focus given to this task has led to an influx of many different architectures of neural networks that are benchmarked against standard datasets like Microsoft’s Common Objects in COntext (COCO). Performance on COCO, a large dataset of computer vision images, is given in terms of mean Average Precision (mAP). In this study, we use six pretrained networks to detect red deer from aerial images, three of which have never been used, to our knowledge, in a context of aerial wildlife surveys. We compare their performance along COCO’s mAP and a common test metric in animal surveys, the F1-score. We also evaluate how dataset imbalance and background uniformity, two common difficulties in wildlife surveys, impact the performance of our models. Our results show that the mAP is not a reliable metric to select the best model to count animals in aerial images and that a counting-focused metric like the F1-score should be favored instead. Our best overall performance was achieved with Generalized Focal Loss (GFL). It scored the highest along both metrics, combining most accurate counting and localization (with average F1-score of 0.96 and 0.97 and average mAP scores of 0.77 and 0.89 on both datasets respectively) and is therefore very promising for future applications. While both imbalance and background uniformity improved the performance of our models, their combined effect had twice as much impact as the choice of architecture. This finding seems to confirm that the recent data-centric shift in the deep learning field could also lead to performance gains in wildlife surveys.
format Online
Article
Text
id pubmed-10124840
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-101248402023-04-25 Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection Moreni, Mael Theau, Jerome Foucher, Samuel PLoS One Research Article The vast amount of images generated by aerial imagery in the context of regular wildlife surveys nowadays require automatic processing tools. At the top of the mountain of different methods to automatically detect objects in images reigns deep learning’s object detection. The recent focus given to this task has led to an influx of many different architectures of neural networks that are benchmarked against standard datasets like Microsoft’s Common Objects in COntext (COCO). Performance on COCO, a large dataset of computer vision images, is given in terms of mean Average Precision (mAP). In this study, we use six pretrained networks to detect red deer from aerial images, three of which have never been used, to our knowledge, in a context of aerial wildlife surveys. We compare their performance along COCO’s mAP and a common test metric in animal surveys, the F1-score. We also evaluate how dataset imbalance and background uniformity, two common difficulties in wildlife surveys, impact the performance of our models. Our results show that the mAP is not a reliable metric to select the best model to count animals in aerial images and that a counting-focused metric like the F1-score should be favored instead. Our best overall performance was achieved with Generalized Focal Loss (GFL). It scored the highest along both metrics, combining most accurate counting and localization (with average F1-score of 0.96 and 0.97 and average mAP scores of 0.77 and 0.89 on both datasets respectively) and is therefore very promising for future applications. While both imbalance and background uniformity improved the performance of our models, their combined effect had twice as much impact as the choice of architecture. This finding seems to confirm that the recent data-centric shift in the deep learning field could also lead to performance gains in wildlife surveys. Public Library of Science 2023-04-24 /pmc/articles/PMC10124840/ /pubmed/37093866 http://dx.doi.org/10.1371/journal.pone.0284449 Text en © 2023 Moreni et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Moreni, Mael
Theau, Jerome
Foucher, Samuel
Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection
title Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection
title_full Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection
title_fullStr Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection
title_full_unstemmed Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection
title_short Do you get what you see? Insights of using mAP to select architectures of pretrained neural networks for automated aerial animal detection
title_sort do you get what you see? insights of using map to select architectures of pretrained neural networks for automated aerial animal detection
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10124840/
https://www.ncbi.nlm.nih.gov/pubmed/37093866
http://dx.doi.org/10.1371/journal.pone.0284449
work_keys_str_mv AT morenimael doyougetwhatyouseeinsightsofusingmaptoselectarchitecturesofpretrainedneuralnetworksforautomatedaerialanimaldetection
AT theaujerome doyougetwhatyouseeinsightsofusingmaptoselectarchitecturesofpretrainedneuralnetworksforautomatedaerialanimaldetection
AT fouchersamuel doyougetwhatyouseeinsightsofusingmaptoselectarchitecturesofpretrainedneuralnetworksforautomatedaerialanimaldetection