Toward bee motion pattern identification on hive landing board

Sledevič, Tomyslav; Abromavičius, Vytautas

doi:10.1109/eStream59056.2023.10134852

Use this URL to cite this publication: https://hdl.handle.net/20.500.14911/115988

Toward bee motion pattern identification on hive landing board

Details

Publication Type (CRIS)

Straipsnis konferencijos medžiagoje Scopus duomenų bazėje / Article in conference proceedings in Scopus database (P1a2)

Publication Type (eLABa)

Straipsnis konferencijos darbų leidinyje Scopus DB / Article in conference proceedings Scopus DB (P1b)

VILNIUS TECH Research Priorities and Topics

Išmaniosios signalų apdorojimo ir ryšių technologijos / Smart Signal Processing and Telecommunication Technologies (IK0202)

Lithuanian Intelligent Specialization

Transportas, logistika ir informacinės ir ryšių technologijos (IRT) / Transport, logistic and information and communication technologies (L106)

Author(s)

Author	Affiliation
Sledevič, Tomyslav	Elektroninių sistemų katedra / Department of Electronic Systems (0549)
Abromavičius, Vytautas	Elektroninių sistemų katedra / Department of Electronic Systems (0549)

Title

Toward bee motion pattern identification on hive landing board

[en]

Tomyslav Sledevič, Vytautas Abromavičius

Is part of

2023 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), 27 April 2023, Vilnius, Lithuania / organized by Vilnius Gediminas Technical University

Published In

Year	Start Page	End Page
2023	1	4

Publisher

Piscataway, NJ : IEEE, 2023

Referenced in Database(s)(DBs)

IEEE Xplore

SCOPUS

Extent

p. 1-4

URI

URI
https://hdl.handle.net/20.500.14911/115988

DOI

10.1109/eStream59056.2023.10134852

Cited references

Science / Art Area

Technologijos mokslai / Technological sciences (T)

Field of Science / Art

Elektros ir elektronikos inžinerija / Electrical and electronic engineering (T001)

Keywords (en)

Abstract (en)

The ability to predict bee behavior through visual analysis of their activity at the hive entrance provides valuable insight into the hive's condition. In this study, we present an algorithm for visual monitoring of bee behavior implemented based on open source tools. The convolutional neural network (CNN) is used to detect bees on the landing board of the hive. The YOLOv8m CNN detects bees with 0.97% mAP@0.5 and 0.65% mAP@0.5:0.95 mean average precision, respectively. Bee behavior types such as foraging, fanning, and washboarding are presented in heat and path maps. The speed patterns are used to identify the type of motion of the bees.