Applying deep learning to right whale photo identification
Abstract Photo identification is an important tool for estimating abundance and monitoring population trends over time. However, manually matching photographs to known individuals is time‐consuming. Motivated by recent developments in image recognition, we hosted a data science challenge on the crow...
Published in: | Conservation Biology |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2018
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1111/cobi.13226 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1111%2Fcobi.13226 https://onlinelibrary.wiley.com/doi/pdf/10.1111/cobi.13226 https://onlinelibrary.wiley.com/doi/full-xml/10.1111/cobi.13226 |
id |
crwiley:10.1111/cobi.13226 |
---|---|
record_format |
openpolar |
spelling |
crwiley:10.1111/cobi.13226 2024-04-07T07:52:16+00:00 Applying deep learning to right whale photo identification Bogucki, Robert Cygan, Marek Khan, Christin Brangwynne Klimek, Maciej Milczek, Jan Kanty Mucha, Marcin 2018 http://dx.doi.org/10.1111/cobi.13226 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1111%2Fcobi.13226 https://onlinelibrary.wiley.com/doi/pdf/10.1111/cobi.13226 https://onlinelibrary.wiley.com/doi/full-xml/10.1111/cobi.13226 en eng Wiley http://creativecommons.org/licenses/by/4.0/ Conservation Biology volume 33, issue 3, page 676-684 ISSN 0888-8892 1523-1739 Nature and Landscape Conservation Ecology Ecology, Evolution, Behavior and Systematics journal-article 2018 crwiley https://doi.org/10.1111/cobi.13226 2024-03-08T03:51:26Z Abstract Photo identification is an important tool for estimating abundance and monitoring population trends over time. However, manually matching photographs to known individuals is time‐consuming. Motivated by recent developments in image recognition, we hosted a data science challenge on the crowdsourcing platform Kaggle to automate the identification of endangered North Atlantic right whales ( Eubalaena glacialis ). The winning solution automatically identified individual whales with 87% accuracy with a series of convolutional neural networks to identify the region of interest on an image, rotate, crop, and create standardized photographs of uniform size and orientation and then identify the correct individual whale from these passport‐like photographs. Recent advances in deep learning coupled with this fully automated workflow have yielded impressive results and have the potential to revolutionize traditional methods for the collection of data on the abundance and distribution of wild populations. Presenting these results to a broad audience should further bridge the gap between the data science and conservation science communities. Article in Journal/Newspaper Eubalaena glacialis North Atlantic Wiley Online Library Conservation Biology 33 3 676 684 |
institution |
Open Polar |
collection |
Wiley Online Library |
op_collection_id |
crwiley |
language |
English |
topic |
Nature and Landscape Conservation Ecology Ecology, Evolution, Behavior and Systematics |
spellingShingle |
Nature and Landscape Conservation Ecology Ecology, Evolution, Behavior and Systematics Bogucki, Robert Cygan, Marek Khan, Christin Brangwynne Klimek, Maciej Milczek, Jan Kanty Mucha, Marcin Applying deep learning to right whale photo identification |
topic_facet |
Nature and Landscape Conservation Ecology Ecology, Evolution, Behavior and Systematics |
description |
Abstract Photo identification is an important tool for estimating abundance and monitoring population trends over time. However, manually matching photographs to known individuals is time‐consuming. Motivated by recent developments in image recognition, we hosted a data science challenge on the crowdsourcing platform Kaggle to automate the identification of endangered North Atlantic right whales ( Eubalaena glacialis ). The winning solution automatically identified individual whales with 87% accuracy with a series of convolutional neural networks to identify the region of interest on an image, rotate, crop, and create standardized photographs of uniform size and orientation and then identify the correct individual whale from these passport‐like photographs. Recent advances in deep learning coupled with this fully automated workflow have yielded impressive results and have the potential to revolutionize traditional methods for the collection of data on the abundance and distribution of wild populations. Presenting these results to a broad audience should further bridge the gap between the data science and conservation science communities. |
format |
Article in Journal/Newspaper |
author |
Bogucki, Robert Cygan, Marek Khan, Christin Brangwynne Klimek, Maciej Milczek, Jan Kanty Mucha, Marcin |
author_facet |
Bogucki, Robert Cygan, Marek Khan, Christin Brangwynne Klimek, Maciej Milczek, Jan Kanty Mucha, Marcin |
author_sort |
Bogucki, Robert |
title |
Applying deep learning to right whale photo identification |
title_short |
Applying deep learning to right whale photo identification |
title_full |
Applying deep learning to right whale photo identification |
title_fullStr |
Applying deep learning to right whale photo identification |
title_full_unstemmed |
Applying deep learning to right whale photo identification |
title_sort |
applying deep learning to right whale photo identification |
publisher |
Wiley |
publishDate |
2018 |
url |
http://dx.doi.org/10.1111/cobi.13226 https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1111%2Fcobi.13226 https://onlinelibrary.wiley.com/doi/pdf/10.1111/cobi.13226 https://onlinelibrary.wiley.com/doi/full-xml/10.1111/cobi.13226 |
genre |
Eubalaena glacialis North Atlantic |
genre_facet |
Eubalaena glacialis North Atlantic |
op_source |
Conservation Biology volume 33, issue 3, page 676-684 ISSN 0888-8892 1523-1739 |
op_rights |
http://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.1111/cobi.13226 |
container_title |
Conservation Biology |
container_volume |
33 |
container_issue |
3 |
container_start_page |
676 |
op_container_end_page |
684 |
_version_ |
1795667536324329472 |