Individual identification of wild raptors using a deep learning approach: A case study of the white-tailed eagle

Individual identification is essential for elucidating animal population structures, tracking population dynamics, and uncovering social networks. Advances in computational technology have enabled the application of deep learning-based methods for individual wildlife identification. However, accurat...

Full description

Saved in:
Bibliographic Details
Main Authors: Xi Guo, Yufeng Chen, Yu Guan, Hongfang Wang, Tianming Wang, Jianping Ge, Lei Bao
Format: Article
Language:English
Published: Elsevier 2025-11-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125003887
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849229316002414592
author Xi Guo
Yufeng Chen
Yu Guan
Hongfang Wang
Tianming Wang
Jianping Ge
Lei Bao
author_facet Xi Guo
Yufeng Chen
Yu Guan
Hongfang Wang
Tianming Wang
Jianping Ge
Lei Bao
author_sort Xi Guo
collection DOAJ
description Individual identification is essential for elucidating animal population structures, tracking population dynamics, and uncovering social networks. Advances in computational technology have enabled the application of deep learning-based methods for individual wildlife identification. However, accurately identifying individual animals in complex wild environments remains a significant challenge. Motivated by the need for accurate and efficient identification of individual animals in the wild, a deep learning-based individual identification framework, the object tracking–face extraction–sampling–recognition (OFSR) approach, is proposed. This framework uses deep learning to extract facial features and a multitask module with cross-task information sharing to integrate supplementary data, enhancing individual identification accuracy. By employing the OFSR framework, we identified individual white-tailed eagles in the Jingxin Wetland during the overwinter period. Our results demonstrated that the OFSR framework could accurately identify individual white-tailed eagles in wild environments, achieving an accuracy exceeding 93 %. In addition, in the multitask module of the OFSR framework, age recognition is used to increase the individual identification accuracy, successfully separating recurring and new individuals and increasing the accuracy by 2 % without adding extra costs. Our results demonstrate the potential of deep learning in identifying individual animals in complex wild environments, and the proposed OFSR framework is universally applicable to other raptors. The findings highlight that the added multitask module increases the accuracy of identifying individual animals. Our framework could improve the accuracy of identifying individuals in complex wild environments, offering a promising method for population detection and conservation research involving wild animals.
format Article
id doaj-art-846c77892ae94886a835bbb1efff3579
institution Kabale University
issn 1574-9541
language English
publishDate 2025-11-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-846c77892ae94886a835bbb1efff35792025-08-22T04:55:56ZengElsevierEcological Informatics1574-95412025-11-019110337910.1016/j.ecoinf.2025.103379Individual identification of wild raptors using a deep learning approach: A case study of the white-tailed eagleXi Guo0Yufeng Chen1Yu Guan2Hongfang Wang3Tianming Wang4Jianping Ge5Lei Bao6Key Laboratory of Environmental Change and Natural Disaster of Chinese Ministry of Education, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaSchool of Mathematical Sciences, Beijing Normal University, Beijing 100875, ChinaMinistry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, College of Life Sciences, Beijing Normal University, Beijing 100875, China; National Forestry and Grassland Administration Key Laboratory for Conservation Ecology of Northeast Tiger and Leopard, Beijing 100875, ChinaMinistry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, College of Life Sciences, Beijing Normal University, Beijing 100875, China; National Forestry and Grassland Administration Key Laboratory for Conservation Ecology of Northeast Tiger and Leopard, Beijing 100875, ChinaMinistry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, College of Life Sciences, Beijing Normal University, Beijing 100875, China; National Forestry and Grassland Administration Key Laboratory for Conservation Ecology of Northeast Tiger and Leopard, Beijing 100875, ChinaMinistry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, College of Life Sciences, Beijing Normal University, Beijing 100875, China; National Forestry and Grassland Administration Key Laboratory for Conservation Ecology of Northeast Tiger and Leopard, Beijing 100875, China; Corresponding authors.Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, College of Life Sciences, Beijing Normal University, Beijing 100875, China; National Forestry and Grassland Administration Key Laboratory for Conservation Ecology of Northeast Tiger and Leopard, Beijing 100875, China; Corresponding authors.Individual identification is essential for elucidating animal population structures, tracking population dynamics, and uncovering social networks. Advances in computational technology have enabled the application of deep learning-based methods for individual wildlife identification. However, accurately identifying individual animals in complex wild environments remains a significant challenge. Motivated by the need for accurate and efficient identification of individual animals in the wild, a deep learning-based individual identification framework, the object tracking–face extraction–sampling–recognition (OFSR) approach, is proposed. This framework uses deep learning to extract facial features and a multitask module with cross-task information sharing to integrate supplementary data, enhancing individual identification accuracy. By employing the OFSR framework, we identified individual white-tailed eagles in the Jingxin Wetland during the overwinter period. Our results demonstrated that the OFSR framework could accurately identify individual white-tailed eagles in wild environments, achieving an accuracy exceeding 93 %. In addition, in the multitask module of the OFSR framework, age recognition is used to increase the individual identification accuracy, successfully separating recurring and new individuals and increasing the accuracy by 2 % without adding extra costs. Our results demonstrate the potential of deep learning in identifying individual animals in complex wild environments, and the proposed OFSR framework is universally applicable to other raptors. The findings highlight that the added multitask module increases the accuracy of identifying individual animals. Our framework could improve the accuracy of identifying individuals in complex wild environments, offering a promising method for population detection and conservation research involving wild animals.http://www.sciencedirect.com/science/article/pii/S1574954125003887Deep learningIndividual identificationOFSR frameworkWhite-tailed eagleWild environment
spellingShingle Xi Guo
Yufeng Chen
Yu Guan
Hongfang Wang
Tianming Wang
Jianping Ge
Lei Bao
Individual identification of wild raptors using a deep learning approach: A case study of the white-tailed eagle
Ecological Informatics
Deep learning
Individual identification
OFSR framework
White-tailed eagle
Wild environment
title Individual identification of wild raptors using a deep learning approach: A case study of the white-tailed eagle
title_full Individual identification of wild raptors using a deep learning approach: A case study of the white-tailed eagle
title_fullStr Individual identification of wild raptors using a deep learning approach: A case study of the white-tailed eagle
title_full_unstemmed Individual identification of wild raptors using a deep learning approach: A case study of the white-tailed eagle
title_short Individual identification of wild raptors using a deep learning approach: A case study of the white-tailed eagle
title_sort individual identification of wild raptors using a deep learning approach a case study of the white tailed eagle
topic Deep learning
Individual identification
OFSR framework
White-tailed eagle
Wild environment
url http://www.sciencedirect.com/science/article/pii/S1574954125003887
work_keys_str_mv AT xiguo individualidentificationofwildraptorsusingadeeplearningapproachacasestudyofthewhitetailedeagle
AT yufengchen individualidentificationofwildraptorsusingadeeplearningapproachacasestudyofthewhitetailedeagle
AT yuguan individualidentificationofwildraptorsusingadeeplearningapproachacasestudyofthewhitetailedeagle
AT hongfangwang individualidentificationofwildraptorsusingadeeplearningapproachacasestudyofthewhitetailedeagle
AT tianmingwang individualidentificationofwildraptorsusingadeeplearningapproachacasestudyofthewhitetailedeagle
AT jianpingge individualidentificationofwildraptorsusingadeeplearningapproachacasestudyofthewhitetailedeagle
AT leibao individualidentificationofwildraptorsusingadeeplearningapproachacasestudyofthewhitetailedeagle