Video based deep learning deciphers honeybee waggle dances in natural conditions

Urbanization and industrial agriculture are a threat to wild and managed honey-bees, crucial pollinators of the natural- and agro-ecosystems components of the landscapes. Understanding bee colonies’ foraging behaviors within these landscapes is essential for managing human-bee conflicts and sustaini...

Descripción completa

Detalles Bibliográficos
Autores principales: Grison, Sylvain, Siddaganga, Rajath, Hedge, Shrihari, Burridge, James, Blok, Pieter M., Krishnan, Smitha, Brockmann, Axel, Guo, Wei
Formato: Journal Article
Lenguaje:Inglés
Publicado: Springer 2025
Materias:
Acceso en línea:https://hdl.handle.net/10568/177838
_version_ 1855535126810722304
author Grison, Sylvain
Siddaganga, Rajath
Hedge, Shrihari
Burridge, James
Blok, Pieter M.
Krishnan, Smitha
Brockmann, Axel
Guo, Wei
author_browse Blok, Pieter M.
Brockmann, Axel
Burridge, James
Grison, Sylvain
Guo, Wei
Hedge, Shrihari
Krishnan, Smitha
Siddaganga, Rajath
author_facet Grison, Sylvain
Siddaganga, Rajath
Hedge, Shrihari
Burridge, James
Blok, Pieter M.
Krishnan, Smitha
Brockmann, Axel
Guo, Wei
author_sort Grison, Sylvain
collection Repository of Agricultural Research Outputs (CGSpace)
description Urbanization and industrial agriculture are a threat to wild and managed honey-bees, crucial pollinators of the natural- and agro-ecosystems components of the landscapes. Understanding bee colonies’ foraging behaviors within these landscapes is essential for managing human-bee conflicts and sustaining their vital pollination services. Objectives To understand how bees use their surroundings, researchers often decode bee waggle dances, a behavior that communicates navigational information about desirable foraging sites to their nest mates. This process is carried out manually, which is time-consuming, prone to human error and requires specialized skills. We aim at developing an automatic pipeline to detect and translate waggle dances in natural conditions. Methods We introduce a novel deep learning-based pipeline that automatically detects and measures waggle runs, the core movement of the waggle dance, under natural recording conditions for the first time. With this information we can estimate the spatial and temporal dynamics of bee foraging behavior. Results Comparison of our pipeline with analysis made by human experts revealed that our procedure is able to detect 100% of waggle runs on the testing dataset, with a run duration Root Mean Squared Error (RMSE) of less than a second, and a run angle RMSE of 0.21 radians. It is also generalizable to other recording conditions and bee species. Conclusion Our approach enables precise measurement of direction and duration, enabling the spatial and temporal analysis of bee foraging behavior on an unprecedented scale compared to traditional manual methods, contributing to preserving biodiversity and ecosystem services.
format Journal Article
id CGSpace177838
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher Springer
publisherStr Springer
record_format dspace
spelling CGSpace1778382025-12-08T10:29:22Z Video based deep learning deciphers honeybee waggle dances in natural conditions Grison, Sylvain Siddaganga, Rajath Hedge, Shrihari Burridge, James Blok, Pieter M. Krishnan, Smitha Brockmann, Axel Guo, Wei machine learning pollination artificial intelligence landscape bees foraging Urbanization and industrial agriculture are a threat to wild and managed honey-bees, crucial pollinators of the natural- and agro-ecosystems components of the landscapes. Understanding bee colonies’ foraging behaviors within these landscapes is essential for managing human-bee conflicts and sustaining their vital pollination services. Objectives To understand how bees use their surroundings, researchers often decode bee waggle dances, a behavior that communicates navigational information about desirable foraging sites to their nest mates. This process is carried out manually, which is time-consuming, prone to human error and requires specialized skills. We aim at developing an automatic pipeline to detect and translate waggle dances in natural conditions. Methods We introduce a novel deep learning-based pipeline that automatically detects and measures waggle runs, the core movement of the waggle dance, under natural recording conditions for the first time. With this information we can estimate the spatial and temporal dynamics of bee foraging behavior. Results Comparison of our pipeline with analysis made by human experts revealed that our procedure is able to detect 100% of waggle runs on the testing dataset, with a run duration Root Mean Squared Error (RMSE) of less than a second, and a run angle RMSE of 0.21 radians. It is also generalizable to other recording conditions and bee species. Conclusion Our approach enables precise measurement of direction and duration, enabling the spatial and temporal analysis of bee foraging behavior on an unprecedented scale compared to traditional manual methods, contributing to preserving biodiversity and ecosystem services. 2025-11-06 2025-11-12T10:33:40Z 2025-11-12T10:33:40Z Journal Article https://hdl.handle.net/10568/177838 en Open Access application/pdf Springer Grison, S.; Siddaganga, R.; Hedge, S.; Burridge, J.; Blok, P.M.; Krishnan, S.; Brockmann, A.; Guo, W. (2025) Video based deep learning deciphers honeybee waggle dances in natural conditions. Landscape Ecology 40(11): 211. ISSN: 0921-2973
spellingShingle machine learning
pollination
artificial intelligence
landscape
bees
foraging
Grison, Sylvain
Siddaganga, Rajath
Hedge, Shrihari
Burridge, James
Blok, Pieter M.
Krishnan, Smitha
Brockmann, Axel
Guo, Wei
Video based deep learning deciphers honeybee waggle dances in natural conditions
title Video based deep learning deciphers honeybee waggle dances in natural conditions
title_full Video based deep learning deciphers honeybee waggle dances in natural conditions
title_fullStr Video based deep learning deciphers honeybee waggle dances in natural conditions
title_full_unstemmed Video based deep learning deciphers honeybee waggle dances in natural conditions
title_short Video based deep learning deciphers honeybee waggle dances in natural conditions
title_sort video based deep learning deciphers honeybee waggle dances in natural conditions
topic machine learning
pollination
artificial intelligence
landscape
bees
foraging
url https://hdl.handle.net/10568/177838
work_keys_str_mv AT grisonsylvain videobaseddeeplearningdeciphershoneybeewaggledancesinnaturalconditions
AT siddagangarajath videobaseddeeplearningdeciphershoneybeewaggledancesinnaturalconditions
AT hedgeshrihari videobaseddeeplearningdeciphershoneybeewaggledancesinnaturalconditions
AT burridgejames videobaseddeeplearningdeciphershoneybeewaggledancesinnaturalconditions
AT blokpieterm videobaseddeeplearningdeciphershoneybeewaggledancesinnaturalconditions
AT krishnansmitha videobaseddeeplearningdeciphershoneybeewaggledancesinnaturalconditions
AT brockmannaxel videobaseddeeplearningdeciphershoneybeewaggledancesinnaturalconditions
AT guowei videobaseddeeplearningdeciphershoneybeewaggledancesinnaturalconditions