BEHAVE - facilitating behaviour coding from videos with AI-detected animals

Applying video recording to investigate behaviour of wild animals reduces field workload, enhances data accuracy, and minimises disturbance to animals. However, extracting information from collected video data remains a cumbersome and time-consuming task if not, at least partly, automated. Recent ad...

Full description

Saved in:
Bibliographic Details
Main Authors: Reinoud Elhorst, Martyna Syposz, Katarzyna Wojczulanis-Jakubas
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125001153
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850201302527639552
author Reinoud Elhorst
Martyna Syposz
Katarzyna Wojczulanis-Jakubas
author_facet Reinoud Elhorst
Martyna Syposz
Katarzyna Wojczulanis-Jakubas
author_sort Reinoud Elhorst
collection DOAJ
description Applying video recording to investigate behaviour of wild animals reduces field workload, enhances data accuracy, and minimises disturbance to animals. However, extracting information from collected video data remains a cumbersome and time-consuming task if not, at least partly, automated. Recent advancements in artificial intelligence (AI) offer automatic detection of target animals in video streams, however integrating these detections with software to annotate behaviours is missing. In addition, programs that are able to do these AI detections are often not easy to install or require specialised hardware to run. To address this gap, we introduce BEHAVE, a user-friendly, open-source, free, zero-install tool for coding animal behaviour in video recordings. BEHAVE can use the results of AI detections to skip sections of the video, can extract timestamps from video data, and supports programmable ethograms. The results are saved in a .csv file for further processing. BEHAVE includes a component that allows doing AI detections, on non-specialised hardware, also in a zero-install, user-friendly way. Due to these advantages, the behaviour coding process can be significantly accelerated, resulting in well-organised and readily exportable/importable data.
format Article
id doaj-art-4722eaa4bb2f4f61863fe6b2dde5ed01
institution OA Journals
issn 1574-9541
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-4722eaa4bb2f4f61863fe6b2dde5ed012025-08-20T02:12:02ZengElsevierEcological Informatics1574-95412025-07-018710310610.1016/j.ecoinf.2025.103106BEHAVE - facilitating behaviour coding from videos with AI-detected animalsReinoud Elhorst0Martyna Syposz1Katarzyna Wojczulanis-Jakubas2Independent Researcher, Haarlem, Netherlands; Corresponding author.University of Gdańsk, Faculty of Biology, Department of Vertebrate Ecology and Zoology, Wita Stwosza 59, 80-308 Gdańsk, PolandUniversity of Gdańsk, Faculty of Biology, Department of Vertebrate Ecology and Zoology, Wita Stwosza 59, 80-308 Gdańsk, PolandApplying video recording to investigate behaviour of wild animals reduces field workload, enhances data accuracy, and minimises disturbance to animals. However, extracting information from collected video data remains a cumbersome and time-consuming task if not, at least partly, automated. Recent advancements in artificial intelligence (AI) offer automatic detection of target animals in video streams, however integrating these detections with software to annotate behaviours is missing. In addition, programs that are able to do these AI detections are often not easy to install or require specialised hardware to run. To address this gap, we introduce BEHAVE, a user-friendly, open-source, free, zero-install tool for coding animal behaviour in video recordings. BEHAVE can use the results of AI detections to skip sections of the video, can extract timestamps from video data, and supports programmable ethograms. The results are saved in a .csv file for further processing. BEHAVE includes a component that allows doing AI detections, on non-specialised hardware, also in a zero-install, user-friendly way. Due to these advantages, the behaviour coding process can be significantly accelerated, resulting in well-organised and readily exportable/importable data.http://www.sciencedirect.com/science/article/pii/S1574954125001153Animal behaviourBehavioural analysisArtificial intelligenceDeep learningImage recognitionContinuous video surveillance
spellingShingle Reinoud Elhorst
Martyna Syposz
Katarzyna Wojczulanis-Jakubas
BEHAVE - facilitating behaviour coding from videos with AI-detected animals
Ecological Informatics
Animal behaviour
Behavioural analysis
Artificial intelligence
Deep learning
Image recognition
Continuous video surveillance
title BEHAVE - facilitating behaviour coding from videos with AI-detected animals
title_full BEHAVE - facilitating behaviour coding from videos with AI-detected animals
title_fullStr BEHAVE - facilitating behaviour coding from videos with AI-detected animals
title_full_unstemmed BEHAVE - facilitating behaviour coding from videos with AI-detected animals
title_short BEHAVE - facilitating behaviour coding from videos with AI-detected animals
title_sort behave facilitating behaviour coding from videos with ai detected animals
topic Animal behaviour
Behavioural analysis
Artificial intelligence
Deep learning
Image recognition
Continuous video surveillance
url http://www.sciencedirect.com/science/article/pii/S1574954125001153
work_keys_str_mv AT reinoudelhorst behavefacilitatingbehaviourcodingfromvideoswithaidetectedanimals
AT martynasyposz behavefacilitatingbehaviourcodingfromvideoswithaidetectedanimals
AT katarzynawojczulanisjakubas behavefacilitatingbehaviourcodingfromvideoswithaidetectedanimals