Analyzing Bee Behavior Through Video Tracking Using Computer Vision Techniques

Ian Carlos Rocha Lima; André Roberto Ortoncelli; Michele Potrich; Marlon Marcon

doi:10.22456/2175-2745.143502

Authors

Ian Carlos Rocha Lima Universidade Tecnólogia Federal do Paraná (UTFPR)
André Roberto Ortoncelli Universidade Tecnológica Federal do Paraná (UTFPR)
Michele Potrich Universidade Tecnólogia Federal do Paraná (UTFPR)
Marlon Marcon Universidade Tecnólogia Federal do Paraná (UTFPR)

DOI:

https://doi.org/10.22456/2175-2745.143502

Keywords:

Insect Detection, Object detection, Heat Maps, Walk Path Analysis

Abstract

Bees are responsible for a large part of the pollination of plant species and act as bioindicators in evaluating phytosanitary products. Research on bee behavior and mortality can be carried out in laboratories with a controlled environment. Still, even so, behavioral assessment, when performed visually by an expert, becomes time-consuming and susceptible to failures, which justifies the creation of automated systems for this purpose. This article presents a tool based on Computer Vision to support this activity. The YOLO/Darknet architecture was used to detect bees in videos, and experiments were carried out with eight pre-trained models, obtaining adequate results of insect detection, which were used to develop an interface that provides graphs and reports: heat maps, walking maps, the percentage of the area explored, the time spent moving, and the speed at which individuals move. Experts can interpret the information produced by the proposed tool to understand bee behavior.

Downloads

Download data is not yet available.

References

NOCELLI, R. et al. Riscos de pesticidas sobre as abelhas. Semana dos Polinizadores, v. 3, p. 196–212, 2012.

KERR, W. E. et al. Aspectos pouco mencionados da biodiversidade amazônica. Parcerias Estratégicas, v. 6, n. 12, p. 20–41, 2010.

SOARES, H. M. Avaliação dos efeitos do inseticida imidacloprido para abelhas sem ferrão Scaptotrigona postica Latreille, 1807 (Hymenoptera, Apidae, Meliponini). Universidade Estadual Paulista (UNESP), 2012.

LOPES, I. S. et al. Agrotóxicos: A ameaça de extinção das abelhas no Brasil. Programa Educativo e Social JC na Escola: Ciência Alimentando o Brasil, p. 95–110, 2018.

GALLO, D. et al. Entomologia agrícola. v. 10. Piracicaba: Fealq, 2002.

JORGE, L. d. C. et al. Software para avaliação do comportamento de insetos. Embrapa Instrumentação-Circular Técnica (INFOTECA-E), São Carlos, SP: Embrapa Instrumentação Agropecuária, 2005. 7 p., 2005.

BILIK, S. et al. Machine learning and computer vision techniques in continuous beehive monitoring applications: A survey. Computers and Electronics in Agriculture, Elsevier, v. 217, p. 108560, 2024.

HORAK, K.; SABLATNIG, R. Deep learning concepts and datasets for image recognition: overview 2019. In: SPIE. International conference on digital image processing. [S.l.], 2019. v. 11179, p. 484–491.

VIOLA, P.; JONES, M. Rapid object detection using a boosted cascade of simple features. In: IEEE. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. [S.l.], 2001. v. 1, p. I–I.

GIRSHICK, R. et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition. [S.l.: s.n.], 2014. p. 580–587.

LIU, W. et al. SSD: Single Shot Multibox Detector. In: SPRINGER. European Conference Computer Vision. [S.l.], 2016. p. 21–37.

REDMON, J. et al. You only look once: Unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition. [s.n.], 2016. p. 779–788. Disponível em: ⟨https://doi.org/10.48550/arXiv.1506.02640⟩.

HUSSAIN, M.; KHANAM, R. In-depth review of YOLOv11 to YOLOv10 variants for enhanced photovoltaic defect detection. In: MDPI. Solar. [S.l.], 2024. v. 4, n. 3, p. 351–386.

BRANSON, K. et al. High-throughput ethomics in large groups of Drosophila. Nature Methods, Nature Publishing Group US New York, v. 6, n. 6, p. 451–457, 2009.

KIMURA, T. et al. Tracking of multiple honey bees on a flat surface. In: IEEE. International Conference on Emerging Trends in Engineering and Technology. 2012. p. 36–39. Disponível em: ⟨https://doi.org/10.1109/ICETET.2012.25⟩.

DICKSON, R. T. et al. Bee traffic estimation with YOLO and optical flow. In: IEEE. SoutheastCon 2024. 2024. p. 928–933. Disponível em: ⟨https://doi.org/10.1109/SoutheastCon52093.2024.10500030⟩.

ZHANG, C.-J. et al. Evaluation of the YOLO models for discrimination of the alfalfa pollinating bee species. Journal of Asia-Pacific Entomology, Elsevier, v. 27, n. 1, p. 102195, 2024. Disponível em: ⟨https://doi.org/10.1016/j.aspen.2023.102195⟩.

KIMURA, T. et al. Development of a new method to track multiple honey bees with complex behaviors on a flat laboratory arena. PLoS ONE, Public Library of Science San Francisco, USA, v. 9, n. 1, p. e84656, 2014. Disponível em: ⟨https://doi.org/10.1371/journal.pone.0084656⟩.