Abstract
Artificial intelligence approaches, such as computer vision, can help better understand the behavior of bees and management. However, the accurate detection and tracking of bee species in the field remain challenging for traditional methods. In this study, we compared YOLOv7 and YOLOv8, two state-of-the-art object detection models, aiming to detect and classify Jataí Brazilian native bees using a custom dataset. Also, we integrated two tracking algorithms (Tracking based on Euclidean distance and ByteTrack) with YOLOv8, yielding a mean average precision (mAP50) of 0.969 and mAP50–95 of 0.682. Additionally, we introduced an optical flow algorithm to monitor beehive entries and exits. We evaluated our approach by comparing it to human performance benchmarks for the same task with and without the aid of technology. Our findings highlight occlusions and outliers (anomalies) as the primary sources of errors in the system. We must consider a coupling of both systems in practical applications because ByteTrack counts bees with an average relative error of 11%, EuclidianTrack monitors incoming bees with 9% (21% if there are outliers), both monitor bees that leave, ByteTrack with 18% if there are outliers, and EuclidianTrack with 33% otherwise. In this way, it is possible to reduce errors of human origin.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hallmann, C.A., et al.: More than 75 percent decline over 27 years in total flying insect biomass in protected areas. PLoS ONE 12, 18–22 (2017). https://doi.org/10.1371/journal.pone.0185809
Arruda, H., Imperatriz-Fonseca, V., de Souza, P., Pessin, G.: Identifying bee species by means of the foraging pattern using machine learning. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2019). https://doi.org/10.1109/IJCNN.2018.8489608
Kuan, A.C., et al.: Sensitivity analyses for simulating pesticide impacts on honey bee colonies. Ecol. Model. 376, 15–27 (2018). https://doi.org/10.1016/j.ecolmodel.2018.02.010
Giannini, T.C., et al.: Climate change in the Eastern Amazon: crop-pollinator and occurrence-restricted bees are potentially more affected. Reg. Environ. Change 20(1), 1–12 (2020). https://doi.org/10.1007/s10113-020-01611-y
Macharia, J.M., Gikungu, M.W., Karanja, R., Okoth, S.: Managed bees as pollinators and vectors of bio control agent against grey mold disease in strawberry plantations. Afr. J. Agric. 16(12), 1674–1680 (2020). https://doi.org/10.5897/AJAR2020.15203
Sánchez-Bayo, F., Wyckhuys, K.A.G.: Worldwide decline of the entomofauna: a review of its drivers. Biol. Cons. 232, 8–27 (2019). https://doi.org/10.1016/j.biocon.2019.01.020
Borges, R.C., Padovani, K., Imperatriz-Fonseca, V.L., Giannini, T.C.: A dataset of multi-functional ecological traits of Brazilian bees. Sci. Data 7(1), 1–9 (2020). https://doi.org/10.1038/s41597-020-0461-3
Gomes, P.A.B., et al.: An Amazon stingless bee foraging activity predicted using recurrent artificial neural networks and attribute selection. Nat. Res. 10(1), 1–12 (2020). https://doi.org/10.1038/s41598-019-56352-8
Filipiak, M.: A better understanding of bee nutritional ecology is needed to optimize conservation strategies for wild bees - the application of ecological stoichiometry. Insects 9(3), 1–13 (2018). https://doi.org/10.3390/insects9030085
Marstaller, J., Tausch, F., Stock, S.: DeepBees - building and scaling convolutional neuronal nets for fast and large-scale visual monitoring of bee hives. In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 271–278. (2019). https://doi.org/10.1109/ICCVW.2019.00036
Xia, D., Chen, P., Wang, B., Zhang, J., Xie, C.: Insect detection and classification based on an improved convolutional neural network. Sensors 18(12), 1–12 (2018). https://doi.org/10.3390/s18124169
Abreu, V.H.R., Pimentel, A.D.A., Absy, M.L., Rech, A.R.: Pollen sources used by Frieseomelitta Ihering 1912 (Hymenoptera: Apidae: Meliponini) bees along the course of the Rio Negro, Amazonas. Brazil. Acta Botanica Brasilica 24(2), 371–383 (2020). https://doi.org/10.1590/0102-33062019abb0391
Júnior, T.C., Rieder, R.: Automatic identification of insects from digital images: a survey. Comput. Electron. Agric. 178(5), 105784 (2020). https://doi.org/10.1016/j.compag.2020.105784
Zhong, Y., Gao, J., Lei, Q., Zhou, Y.: A vision-based counting and recognition system for flying insects in intelligent agriculture. Sensors 18(5), 1489 (2018). https://doi.org/10.3390/s18051489
Qing, Y., et al.: Development of an automatic monitoring system for rice light-trap pests based on machine vision. J. Integr. Agric. 19(10), 2500–2513 (2020). https://doi.org/10.1016/S2095-3119(20)63168-9
Shen, Y., Zhou, H., Li, J., Jian, F., Jayas, D.S.: Detection of stored-grain insects using deep learning. Comput. Electron. Agric. 145, 319–325 (2018). https://doi.org/10.1016/j.compag.2017.11.039
Liu, L., et al.: PestNet: an end-to-end deep learning approach for large-scale multi-class pest detection and classification. IEEE Acess 7, 45301–45312 (2019). https://doi.org/10.1109/ACCESS.2019.2909522
Fujioka, H., Abe, M.S., Okada, Y.: Ant activity-rest rhythms vary with age and interaction frequencies of workers. Behav. Ecol. Sociobiol. 73(3), 30 (2019). https://doi.org/10.1007/s00265-019-2641-8
Fujioka, H., Abe, M.S., Okada, Y.: Individual ants do not show activity-rest rhythms in nest conditions. J. Biol. Rhythms 36(3), 297–310 (2021). https://doi.org/10.1177/07487304211002934
Ratnayake, M.N., Dyer, A.G., Dorin, A.: Tracking individual honeybees among wildflower clusters with computer vision-facilitated pollinator monitoring. PLoS ONE 16(2), e0239504 (2021). https://doi.org/10.1371/journal.pone.0239504
Lima, M.C.F., Leandro, M.E.D.A., Valero, C., Coronel, L.C.P., Bazzo, C.O.G.: Automatic detection and monitoring of insect pests - a review. Agriculture 10(5), 161 (2020). https://doi.org/10.3390/agriculture10050161
Imirzian, N., et al.: Automated tracking and analysis of ant trajectories shows variation in forager exploration. Sci. Rep. 9(1), 1 (2019). https://doi.org/10.1038/s41598-019-49655-3
Sclocco, A., Ong, S.J.Y., Aung, S.Y.P., Teseo, S.: Integrating real-time data analysis into automatic tracking of social insects. R. Soc. Open Sci. 8(3), 202033 (2021). https://doi.org/10.1098/rsos.202033
Tathawee, T., Wattanachaiyingcharoen, W., Suwannakom, A., Prasarnpun, S.: Flash communication pattern analysis of fireflies based on computer vision. Int. J. Adv. Intell. Inf. 6(1), 60–71 (2020). https://doi.org/10.26555/ijain.v6i1.367
Bjerge, K., Nielsen, J.B., Sepstrup, M.V., Helsing-Nielsen, F., Hoye, T.T.: An automated light trap to monitor moths (Lepidoptera) using computer vision-based tracking and deep learning. Sensors 21(2), 343 (2021). https://doi.org/10.3390/s21020343
Howard, S.R., Ratnayake, M.N., Dyer, A.G., Garcia, J.E., Dorin, A.: Towards precision apiculture: traditional and technological insect monitoring methods in strawberry and raspberry crop polytunnels tell different pollination stories. PLoS ON 16(5), e0251572 (2021). https://doi.org/10.1371/journal.pone.0251572
Perez-Cham, O.E., et al.: Parallelization of the honeybee search algorithm for object tracking. Appl. Sci. 10(6), 2122 (2020). https://doi.org/10.3390/app10062122
Sun, C., Gaydecki, P.: A visual tracking system for honey bee (Hymenoptera: Apidae) 3D flight trajectory reconstruction and analysis. J. Insect Sci. 21(2), 1–12 (2021). https://doi.org/10.1093/jisesa/ieab023
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2016)
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint: arXiv:1804.02767 (2018)
Bochkovskiy, A., Wang, C., Liao, H.M.: YOLOv4: optimal speed and accuracy of object detection. Cornell Univ. arXiv preprint: arXiv:2004.10934 (2020)
Jocher, G.: ultralytics/yolov5: v3.1. (2020). https://doi.org/10.5281/zenodo.4154370
Li, C., et al.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint: arXiv:2207.02696 (2022)
Wang, C., Bochkovskiy, A., Liao, H.M.: Designing network design strategies through gradient path analysis. arXiv preprint: arXiv:2211.04800 (2022)
Jocher, G., Chaurasia, A., Qiu, J.: YOLO by Ultralytics v8. (2023)
Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. In: Proceedings of the European Conference on Computer Vision (2022)
Dendorfer, P., et al.: MOT20: a benchmark for multi object tracking in crowded scenes. arXiv:2003.09003 [cs] (2020)
Acknowledgments
The authors would like to thank the Universidade de São Paulo (USP BeeKeep CS - https://beekeep.pcs.usp.br), the Empresa Brasileira de Pesquisa Agropecuária (Embrapa), and the Associação Brasileira de Estudo das Abelhas (A.B.E.L.H.A. - https://abelha.org.br) by the data and videos. People who allowed filmings on their properties. To the Laboratório Multiusuário de Práticas Simuladas (LaMPS - https://lamps.medicina.ufop.br) and the Laboratório de Controle e Automação Multiusuário (LABCAM) for the infrastructure and equipment provided. Google Collaboratory by the technologies that make AI research possible with scarce resources. To Carlos J. Pereira, Eduardo Carvalho, Levi W. R. Filho, and André A. Santos (Instituto Tecnológico Vale) along with Diego M. Alberto (Efí) for their support with the computational methods. This research received financial support from the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brazil (CAPES) - Financing code 001.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Leocádio, R.R.V., Segundo, A.K.R., Pessin, G. (2023). Multiple Object Tracking in Native Bee Hives: A Case Study with Jataí in the Field. In: Naldi, M.C., Bianchi, R.A.C. (eds) Intelligent Systems. BRACIS 2023. Lecture Notes in Computer Science(), vol 14197. Springer, Cham. https://doi.org/10.1007/978-3-031-45392-2_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-45392-2_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45391-5
Online ISBN: 978-3-031-45392-2
eBook Packages: Computer ScienceComputer Science (R0)