Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus )
The ability to re-identify individuals is fundamental to the individual-based studies that are required to estimate many important ecological and evolutionary parameters in wild populations. Traditional methods of marking individuals and tracking them through time can be invasive and imperfect, whic...
Published in: | Royal Society Open Science |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
The Royal Society
2021
|
Subjects: | |
Online Access: | https://doi.org/10.1098/rsos.201768 https://doaj.org/article/b35c3168dec5459782719dc5d58c8fd8 |
id |
ftdoajarticles:oai:doaj.org/article:b35c3168dec5459782719dc5d58c8fd8 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:b35c3168dec5459782719dc5d58c8fd8 2023-05-15T14:30:06+02:00 Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus ) Ignacy T. Dȩbicki Elizabeth A. Mittell Bjarni K. Kristjánsson Camille A. Leblanc Michael B. Morrissey Kasim Terzić 2021-07-01T00:00:00Z https://doi.org/10.1098/rsos.201768 https://doaj.org/article/b35c3168dec5459782719dc5d58c8fd8 EN eng The Royal Society https://royalsocietypublishing.org/doi/10.1098/rsos.201768 https://doaj.org/toc/2054-5703 doi:10.1098/rsos.201768 2054-5703 https://doaj.org/article/b35c3168dec5459782719dc5d58c8fd8 Royal Society Open Science, Vol 8, Iss 7 (2021) individual re-identification photo identification deep-learning spot extraction spot matching capture–mark–recapture Science Q article 2021 ftdoajarticles https://doi.org/10.1098/rsos.201768 2022-12-31T06:48:55Z The ability to re-identify individuals is fundamental to the individual-based studies that are required to estimate many important ecological and evolutionary parameters in wild populations. Traditional methods of marking individuals and tracking them through time can be invasive and imperfect, which can affect these estimates and create uncertainties for population management. Here we present a photographic re-identification method that uses spot constellations in images to match specimens through time. Photographs of Arctic charr (Salvelinus alpinus) were used as a case study. Classical computer vision techniques were compared with new deep-learning techniques for masks and spot extraction. We found that a U-Net approach trained on a small set of human-annotated photographs performed substantially better than a baseline feature engineering approach. For matching the spot constellations, two algorithms were adapted, and, depending on whether a fully or semi-automated set-up is preferred, we show how either one or a combination of these algorithms can be implemented. Within our case study, our pipeline both successfully identified unmarked individuals from photographs alone and re-identified individuals that had lost tags, resulting in an approximately 4% increase in our estimate of survival rate. Overall, our multi-step pipeline involves little human supervision and could be applied to many organisms. Article in Journal/Newspaper Arctic charr Arctic Salvelinus alpinus Directory of Open Access Journals: DOAJ Articles Arctic Royal Society Open Science 8 7 201768 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
individual re-identification photo identification deep-learning spot extraction spot matching capture–mark–recapture Science Q |
spellingShingle |
individual re-identification photo identification deep-learning spot extraction spot matching capture–mark–recapture Science Q Ignacy T. Dȩbicki Elizabeth A. Mittell Bjarni K. Kristjánsson Camille A. Leblanc Michael B. Morrissey Kasim Terzić Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus ) |
topic_facet |
individual re-identification photo identification deep-learning spot extraction spot matching capture–mark–recapture Science Q |
description |
The ability to re-identify individuals is fundamental to the individual-based studies that are required to estimate many important ecological and evolutionary parameters in wild populations. Traditional methods of marking individuals and tracking them through time can be invasive and imperfect, which can affect these estimates and create uncertainties for population management. Here we present a photographic re-identification method that uses spot constellations in images to match specimens through time. Photographs of Arctic charr (Salvelinus alpinus) were used as a case study. Classical computer vision techniques were compared with new deep-learning techniques for masks and spot extraction. We found that a U-Net approach trained on a small set of human-annotated photographs performed substantially better than a baseline feature engineering approach. For matching the spot constellations, two algorithms were adapted, and, depending on whether a fully or semi-automated set-up is preferred, we show how either one or a combination of these algorithms can be implemented. Within our case study, our pipeline both successfully identified unmarked individuals from photographs alone and re-identified individuals that had lost tags, resulting in an approximately 4% increase in our estimate of survival rate. Overall, our multi-step pipeline involves little human supervision and could be applied to many organisms. |
format |
Article in Journal/Newspaper |
author |
Ignacy T. Dȩbicki Elizabeth A. Mittell Bjarni K. Kristjánsson Camille A. Leblanc Michael B. Morrissey Kasim Terzić |
author_facet |
Ignacy T. Dȩbicki Elizabeth A. Mittell Bjarni K. Kristjánsson Camille A. Leblanc Michael B. Morrissey Kasim Terzić |
author_sort |
Ignacy T. Dȩbicki |
title |
Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus ) |
title_short |
Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus ) |
title_full |
Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus ) |
title_fullStr |
Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus ) |
title_full_unstemmed |
Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus ) |
title_sort |
re-identification of individuals from images using spot constellations: a case study in arctic charr ( salvelinus alpinus ) |
publisher |
The Royal Society |
publishDate |
2021 |
url |
https://doi.org/10.1098/rsos.201768 https://doaj.org/article/b35c3168dec5459782719dc5d58c8fd8 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic charr Arctic Salvelinus alpinus |
genre_facet |
Arctic charr Arctic Salvelinus alpinus |
op_source |
Royal Society Open Science, Vol 8, Iss 7 (2021) |
op_relation |
https://royalsocietypublishing.org/doi/10.1098/rsos.201768 https://doaj.org/toc/2054-5703 doi:10.1098/rsos.201768 2054-5703 https://doaj.org/article/b35c3168dec5459782719dc5d58c8fd8 |
op_doi |
https://doi.org/10.1098/rsos.201768 |
container_title |
Royal Society Open Science |
container_volume |
8 |
container_issue |
7 |
container_start_page |
201768 |
_version_ |
1766304016418996224 |