Non-invasive Honeybee Colony Monitoring via Robotic Mapping of Combs in Observation Hives

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00385798" target="_blank" >RIV/68407700:21230/25:00385798 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1016/j.compag.2025.111031" target="_blank" >https://doi.org/10.1016/j.compag.2025.111031</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.compag.2025.111031" target="_blank" >10.1016/j.compag.2025.111031</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Non-invasive Honeybee Colony Monitoring via Robotic Mapping of Combs in Observation Hives

Popis výsledku v původním jazyce

Honeybees play a crucial role in our ecosystem, as their pollination efforts directly affect the global food web and biodiversity of flowering plants. Consequently, in light of the worldwide decline of pollinators, understanding the dynamics of honeybee colonies and monitoring their health attracted high research interest. One possible approach to health assessments is to estimate the number of brood and food storage cells in the honeybee comb. However, the cells are difficult to observe directly due to occlusions caused by the worker bees. This requires either manual removal of the comb and brushing off the bees, or continuous monitoring of the entire comb. In this work, we present a method for automated monitoring of brood cells over long time periods by a robot operating in observation hive. Our approach uses focused honeybee queen observations to detect egg-laying events and opportunistic and irregular image scans to detect and classify individual cells in the comb. By combining these modules with a temporal model of brood development, we create a spatially and temporally consistent semantic map of the comb. The resulting map allows us to continuously estimate the total numbers of different brood cell types in the comb, as well as the brood cannibalism rate. Although the robotic platform used in this study is not applicable to standard hives, our work contributes valuable data for modeling honeybee colonies and understanding the structural dynamics of the comb.

Název v anglickém jazyce

Non-invasive Honeybee Colony Monitoring via Robotic Mapping of Combs in Observation Hives

Popis výsledku anglicky

Honeybees play a crucial role in our ecosystem, as their pollination efforts directly affect the global food web and biodiversity of flowering plants. Consequently, in light of the worldwide decline of pollinators, understanding the dynamics of honeybee colonies and monitoring their health attracted high research interest. One possible approach to health assessments is to estimate the number of brood and food storage cells in the honeybee comb. However, the cells are difficult to observe directly due to occlusions caused by the worker bees. This requires either manual removal of the comb and brushing off the bees, or continuous monitoring of the entire comb. In this work, we present a method for automated monitoring of brood cells over long time periods by a robot operating in observation hive. Our approach uses focused honeybee queen observations to detect egg-laying events and opportunistic and irregular image scans to detect and classify individual cells in the comb. By combining these modules with a temporal model of brood development, we create a spatially and temporally consistent semantic map of the comb. The resulting map allows us to continuously estimate the total numbers of different brood cell types in the comb, as well as the brood cannibalism rate. Although the robotic platform used in this study is not applicable to standard hives, our work contributes valuable data for modeling honeybee colonies and understanding the structural dynamics of the comb.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotika a pokročilá průmyslová výroba</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Computers and Electronics in Agriculture

ISSN

0168-1699

e-ISSN

1872-7107

Svazek periodika

239

Číslo periodika v rámci svazku

C

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

21

Strana od-do

1-21

Kód UT WoS článku

001599217200001

EID výsledku v databázi Scopus

2-s2.0-105018672956