Applying a YOLO model to detect and differentiate honeybee castes by image in a automated way
Abstract
In a honeybee colony (Apis mellifera L.) there are three types of caste: queen, worker and drone. Detecting and differentiating them is of paramount importance for the beekeeper, as unusual fluctuation and umbalance in the number and natural proportion among these individuals provide predictions about events that can negatively impact the welfare and production of the colony. In this article, we apply the concept of Digital Image Processing, through the YOLO object detector, to differentiate drones and workers of honeybees in order to provide subsidies for the advancement of precision beekeeping. Through cross-validation, the chosen architecture correctly recognized and classified most of the bees present in the images, obtaining values of mAP@50 above 94%. Furthermore, even with an unbalanced dataset and most of the bees being worker bees, the proposed model was able to find and classify most drones, reflecting recall values above 85%.
Keywords:
honeybees, digital image processing, computer vision, deep learning
References
Barros, C., Freitas, E. D., Braga, A. R., Bomfim, I. G., and Gomes, D. (2021). Aplicando redes neurais convolucionais em imagens para reconhecimento automatizado de abelhas melíferas (Apis mellifera l.). In Anais do XIIWorkshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 19–28, Porto Alegre, RS, Brasil. SBC. https://doi.org/10.5753/wcama.2021.15733.
Bilik, S., Kratochvila, L., Ligocki, A., Bostik, O., Zemcik, T., Hybl, M., Horak, K., and Zalud, L. (2021). Visual diagnosis of the varroa destructor parasitic mite in honeybees using object detector techniques. Sensors, 21(8). https://doi.org/10.3390/s21082764.
Braga, A. R., G. Gomes, D., Rogers, R., E. Hassler, E., M. Freitas, B., and A. Cazier, J. (2020). A method for mining combined data from in-hive sensors, weather and apiary inspections to forecast the health status of honey bee colonies. Computers and Electronics in Agriculture, 169:105161. https://doi.org/10.1016/j.compag.2019.105161.
Couto, R. H. N. and Couto, L. A. (2006). Apicultura: manejo e produtos. Funep Jaboticabal. De Cesaro Júnior, T. and Rieder, R. (2020). Automatic identification of insects from digital images: A survey. Computers and Electronics in Agriculture, 178:105784. https://doi.org/10.1016/j.compag.2020.105784.
Debauche, O., Moulat, M. E., Mahmoudi, S., Boukraa, S., Manneback, P., and Lebeau, F. (2018). Web monitoring of bee health for researchers and beekeepers based on the internet of things. Procedia Computer Science, 130:991–998. The 9th International Conference on Ambient Systems, Networks and Technologies (ANT 2018) / The 8th International Conference on Sustainable Energy Information Technology (SEIT-2018) / Affiliated Workshops. https://doi.org/10.1016/j.procs.2018.04.103.
Hadjur, H., Ammar, D., and Lefèvre, L. (2022). Toward an intelligent and efficient beehive: A survey of precision beekeeping systems and services. Computers and Electronics in Agriculture, 192:106604. https://doi.org/10.1016/j.compag.2021.106604.
Hui, J. (2018). map (mean average precision) for object detection. Disponível em: [link]. Acesso em: 03 mar. 2022.
Jocher, G., Nishimura, K., Mineeva, T., and Vilariño, R. (2020). Yolov5 by ultralytics. Disponível em: https://github.com/ultralytics/yolov5.
Kevan, P. G. et al. (2007). Bees, biology & management. Enviroquest.
Kubera, E., Kubik-Komar, A., Kurasínski, P., Piotrowska-Weryszko, K., and Skrzypiec, M. (2022). Detection and recognition of pollen grains in multilabel microscopic images. Sensors, 22(7). https://doi.org/10.3390/s22072690.
Leocádio, R., Segundo, A., Souza, J., Galaschi-Teixeira, J., Souza, P., and Pessin, G. (2021). Detecção de abelhas nativas em colmeias em campo utilizando visão computacional. In Anais do XII Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 59–68, Porto Alegre, RS, Brasil. SBC.
Lin, T., Maire, M., Belongie, S. J., Bourdev, L. D., Girshick, R. B., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft COCO: common objects in context. CoRR, abs/1405.0312. https://doi.org/10.48550/arXiv.1405.0312.
Padilla, R., Netto, S. L., and da Silva, E. A. B. (2020). A survey on performance metrics for object-detection algorithms. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), pages 237–242. https://doi.org/10.1109/IWSSIP48289.2020.9145130.
Potts, S. G., Imperatriz Fonseca, V., Ngo, H. T., Biesmeijer, J. C., Breeze, T. D., Dicks, L., Garibaldi, L. A., Hill, R., Settele, J., Vanbergen, A. J., et al. (2016). Summary for policymakers of the assessment report of the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services on pollinators, pollination and food production. Intergovernmental SciencePolicy Platform on Biodiversity and Ecosystem Services.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788.
Seeley, T. (2006). Ecologia da Abelha: um estudo de adaptação na vida social (tradução de CA Osowski). LTDA, Porto Alegre.
Soroye, P., Newbold, T., and Kerr, J. (2020). Climate change contributes to widespread declines among bumble bees across continents. Science, 367(6478):685–688. https://doi.org/10.1126/science.aax8591.
Tashakkori, R., Hamza, A. S., and Crawford, M. B. (2021). Beemon: An iot-based beehive monitoring system. Computers and Electronics in Agriculture, 190:106427. https://doi.org/10.1016/j.compag.2021.106427.
Watanabe, M. E. (2013). Pollinators at Risk: Human activities threaten key species. BioScience, 64(1):5–10. https://doi.org/10.1093/biosci/bit012.
Wiese, H. (2005). Apicultura: novos tempos. Agrolivros Porto Alegre.
Winston, M. (2003). A biologia da abelha. Tradução de Carlos A. Osowski. Magister. Porto Alegre.
Yan, B., Fan, P., Lei, X., Liu, Z., and Yang, F. (2021). A real-time apple targets detection method for picking robot based on improved yolov5. Remote Sensing, 13(9). https://doi.org/10.3390/rs13091619.
Bilik, S., Kratochvila, L., Ligocki, A., Bostik, O., Zemcik, T., Hybl, M., Horak, K., and Zalud, L. (2021). Visual diagnosis of the varroa destructor parasitic mite in honeybees using object detector techniques. Sensors, 21(8). https://doi.org/10.3390/s21082764.
Braga, A. R., G. Gomes, D., Rogers, R., E. Hassler, E., M. Freitas, B., and A. Cazier, J. (2020). A method for mining combined data from in-hive sensors, weather and apiary inspections to forecast the health status of honey bee colonies. Computers and Electronics in Agriculture, 169:105161. https://doi.org/10.1016/j.compag.2019.105161.
Couto, R. H. N. and Couto, L. A. (2006). Apicultura: manejo e produtos. Funep Jaboticabal. De Cesaro Júnior, T. and Rieder, R. (2020). Automatic identification of insects from digital images: A survey. Computers and Electronics in Agriculture, 178:105784. https://doi.org/10.1016/j.compag.2020.105784.
Debauche, O., Moulat, M. E., Mahmoudi, S., Boukraa, S., Manneback, P., and Lebeau, F. (2018). Web monitoring of bee health for researchers and beekeepers based on the internet of things. Procedia Computer Science, 130:991–998. The 9th International Conference on Ambient Systems, Networks and Technologies (ANT 2018) / The 8th International Conference on Sustainable Energy Information Technology (SEIT-2018) / Affiliated Workshops. https://doi.org/10.1016/j.procs.2018.04.103.
Hadjur, H., Ammar, D., and Lefèvre, L. (2022). Toward an intelligent and efficient beehive: A survey of precision beekeeping systems and services. Computers and Electronics in Agriculture, 192:106604. https://doi.org/10.1016/j.compag.2021.106604.
Hui, J. (2018). map (mean average precision) for object detection. Disponível em: [link]. Acesso em: 03 mar. 2022.
Jocher, G., Nishimura, K., Mineeva, T., and Vilariño, R. (2020). Yolov5 by ultralytics. Disponível em: https://github.com/ultralytics/yolov5.
Kevan, P. G. et al. (2007). Bees, biology & management. Enviroquest.
Kubera, E., Kubik-Komar, A., Kurasínski, P., Piotrowska-Weryszko, K., and Skrzypiec, M. (2022). Detection and recognition of pollen grains in multilabel microscopic images. Sensors, 22(7). https://doi.org/10.3390/s22072690.
Leocádio, R., Segundo, A., Souza, J., Galaschi-Teixeira, J., Souza, P., and Pessin, G. (2021). Detecção de abelhas nativas em colmeias em campo utilizando visão computacional. In Anais do XII Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 59–68, Porto Alegre, RS, Brasil. SBC.
Lin, T., Maire, M., Belongie, S. J., Bourdev, L. D., Girshick, R. B., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft COCO: common objects in context. CoRR, abs/1405.0312. https://doi.org/10.48550/arXiv.1405.0312.
Padilla, R., Netto, S. L., and da Silva, E. A. B. (2020). A survey on performance metrics for object-detection algorithms. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), pages 237–242. https://doi.org/10.1109/IWSSIP48289.2020.9145130.
Potts, S. G., Imperatriz Fonseca, V., Ngo, H. T., Biesmeijer, J. C., Breeze, T. D., Dicks, L., Garibaldi, L. A., Hill, R., Settele, J., Vanbergen, A. J., et al. (2016). Summary for policymakers of the assessment report of the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services on pollinators, pollination and food production. Intergovernmental SciencePolicy Platform on Biodiversity and Ecosystem Services.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788.
Seeley, T. (2006). Ecologia da Abelha: um estudo de adaptação na vida social (tradução de CA Osowski). LTDA, Porto Alegre.
Soroye, P., Newbold, T., and Kerr, J. (2020). Climate change contributes to widespread declines among bumble bees across continents. Science, 367(6478):685–688. https://doi.org/10.1126/science.aax8591.
Tashakkori, R., Hamza, A. S., and Crawford, M. B. (2021). Beemon: An iot-based beehive monitoring system. Computers and Electronics in Agriculture, 190:106427. https://doi.org/10.1016/j.compag.2021.106427.
Watanabe, M. E. (2013). Pollinators at Risk: Human activities threaten key species. BioScience, 64(1):5–10. https://doi.org/10.1093/biosci/bit012.
Wiese, H. (2005). Apicultura: novos tempos. Agrolivros Porto Alegre.
Winston, M. (2003). A biologia da abelha. Tradução de Carlos A. Osowski. Magister. Porto Alegre.
Yan, B., Fan, P., Lei, X., Liu, Z., and Yang, F. (2021). A real-time apple targets detection method for picking robot based on improved yolov5. Remote Sensing, 13(9). https://doi.org/10.3390/rs13091619.
Published
2022-07-31
How to Cite
ALBUQUERQUE, Davi Queiroz; BRAGA, Antonio Rafael; BOMFIM, Isac Gabriel Abrahão; GOMES, Danielo G..
Applying a YOLO model to detect and differentiate honeybee castes by image in a automated way. In: WORKSHOP ON COMPUTING APPLIED TO THE MANAGEMENT OF THE ENVIRONMENT AND NATURAL RESOURCES (WCAMA), 13. , 2022, Niterói.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 51-60.
ISSN 2595-6124.
DOI: https://doi.org/10.5753/wcama.2022.222918.
