Counting using deep learning regression gives value to ecological surveys

Abstract Many ecological studies rely on count data and involve manual counting of objects of interest, which is time-consuming and especially disadvantageous when time in the field or lab is limited. However, an increasing number of works uses digital imagery, which opens opportunities to automatis...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jeroen P. A. Hoekendijk, Benjamin Kellenberger, Geert Aarts, Sophie Brasseur, Suzanne S. H. Poiesz, Devis Tuia
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/63ae53169aa442958faa213431cc04de
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:63ae53169aa442958faa213431cc04de
record_format	dspace
spelling	oai:doaj.org-article:63ae53169aa442958faa213431cc04de2021-12-05T12:12:25ZCounting using deep learning regression gives value to ecological surveys10.1038/s41598-021-02387-92045-2322https://doaj.org/article/63ae53169aa442958faa213431cc04de2021-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-02387-9https://doaj.org/toc/2045-2322Abstract Many ecological studies rely on count data and involve manual counting of objects of interest, which is time-consuming and especially disadvantageous when time in the field or lab is limited. However, an increasing number of works uses digital imagery, which opens opportunities to automatise counting tasks. In this study, we use machine learning to automate counting objects of interest without the need to label individual objects. By leveraging already existing image-level annotations, this approach can also give value to historical data that were collected and annotated over longer time series (typical for many ecological studies), without the aim of deep learning applications. We demonstrate deep learning regression on two fundamentally different counting tasks: (i) daily growth rings from microscopic images of fish otolith (i.e., hearing stone) and (ii) hauled out seals from highly variable aerial imagery. In the otolith images, our deep learning-based regressor yields an RMSE of 3.40 day-rings and an $$R^2$$ R 2 of 0.92. Initial performance in the seal images is lower (RMSE of 23.46 seals and $$R^2$$ R 2 of 0.72), which can be attributed to a lack of images with a high number of seals in the initial training set, compared to the test set. We then show how to improve performance substantially (RMSE of 19.03 seals and $$R^2$$ R 2 of 0.77) by carefully selecting and relabelling just 100 additional training images based on initial model prediction discrepancy. The regression-based approach used here returns accurate counts ( $$R^2$$ R 2 of 0.92 and 0.77 for the rings and seals, respectively), directly usable in ecological research.Jeroen P. A. HoekendijkBenjamin KellenbergerGeert AartsSophie BrasseurSuzanne S. H. PoieszDevis TuiaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jeroen P. A. Hoekendijk Benjamin Kellenberger Geert Aarts Sophie Brasseur Suzanne S. H. Poiesz Devis Tuia Counting using deep learning regression gives value to ecological surveys
description	Abstract Many ecological studies rely on count data and involve manual counting of objects of interest, which is time-consuming and especially disadvantageous when time in the field or lab is limited. However, an increasing number of works uses digital imagery, which opens opportunities to automatise counting tasks. In this study, we use machine learning to automate counting objects of interest without the need to label individual objects. By leveraging already existing image-level annotations, this approach can also give value to historical data that were collected and annotated over longer time series (typical for many ecological studies), without the aim of deep learning applications. We demonstrate deep learning regression on two fundamentally different counting tasks: (i) daily growth rings from microscopic images of fish otolith (i.e., hearing stone) and (ii) hauled out seals from highly variable aerial imagery. In the otolith images, our deep learning-based regressor yields an RMSE of 3.40 day-rings and an $$R^2$$ R 2 of 0.92. Initial performance in the seal images is lower (RMSE of 23.46 seals and $$R^2$$ R 2 of 0.72), which can be attributed to a lack of images with a high number of seals in the initial training set, compared to the test set. We then show how to improve performance substantially (RMSE of 19.03 seals and $$R^2$$ R 2 of 0.77) by carefully selecting and relabelling just 100 additional training images based on initial model prediction discrepancy. The regression-based approach used here returns accurate counts ( $$R^2$$ R 2 of 0.92 and 0.77 for the rings and seals, respectively), directly usable in ecological research.
format	article
author	Jeroen P. A. Hoekendijk Benjamin Kellenberger Geert Aarts Sophie Brasseur Suzanne S. H. Poiesz Devis Tuia
author_facet	Jeroen P. A. Hoekendijk Benjamin Kellenberger Geert Aarts Sophie Brasseur Suzanne S. H. Poiesz Devis Tuia
author_sort	Jeroen P. A. Hoekendijk
title	Counting using deep learning regression gives value to ecological surveys
title_short	Counting using deep learning regression gives value to ecological surveys
title_full	Counting using deep learning regression gives value to ecological surveys
title_fullStr	Counting using deep learning regression gives value to ecological surveys
title_full_unstemmed	Counting using deep learning regression gives value to ecological surveys
title_sort	counting using deep learning regression gives value to ecological surveys
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/63ae53169aa442958faa213431cc04de
work_keys_str_mv	AT jeroenpahoekendijk countingusingdeeplearningregressiongivesvaluetoecologicalsurveys AT benjaminkellenberger countingusingdeeplearningregressiongivesvaluetoecologicalsurveys AT geertaarts countingusingdeeplearningregressiongivesvaluetoecologicalsurveys AT sophiebrasseur countingusingdeeplearningregressiongivesvaluetoecologicalsurveys AT suzanneshpoiesz countingusingdeeplearningregressiongivesvaluetoecologicalsurveys AT devistuia countingusingdeeplearningregressiongivesvaluetoecologicalsurveys
_version_	1718372136499806208

Counting using deep learning regression gives value to ecological surveys

Ejemplares similares