Detection of Native Bees in Field Hives Using Computer Vision

• Rodolfo R. V. Leocádio UFOP
• Alan K. R. Segundo UFOP
• Jefferson R. Souza UFU
• Juliana Galaschi-Teixeira ITV
• Paulo de Souza Griffith University
• Gustavo Pessin UFOP / ITV

DOI: https://doi.org/10.5753/wcama.2021.15737

Abstract

Artificial intelligence approaches can, like computer vision, help improve the understanding behavior of bee species. Accurate detection of bees in the field is challenging. We investigate the use of the detector YOLO in the task of species recognition; with benefits from its speed and generalization. YOLO detected most bees present in the frames, with an effectiveness mAP of 99.5%.

Keywords: Artificial Intelligence, Computer Vision, Bee Species

References

Arruda, H., Imperatriz-fonseca, V., De Souza, P. e Pessin, G. (2018) “Identifying Bee Species by Means of the Foraging Pattern Using Machine Learning”, in 2018 International Joint Conference on Neural Networks (IJCNN), p. 1-6.

Bochkovskiy, A., Wang, C. e Liao, H. M. (2020) “YOLOv4: Optimal Speed and Accuracy of Object Detection”, Cornell Univ., no. April. arXiv:2004.10934v1

Borges, R. C., Padovani, K., Imperatriz-Fonseca, V. L. e Giannini, T. C. (2020) “A dataset of multi-functional ecological traits of Brazilian bees”, Sci. Data, vol. 7, p. 1-9. doi: https://doi.org/10.1038/s41597-020-0461-3

Costa, L. (2019) Guia Fotográfico de Identificação de Abelhas Sem Ferrão, para resgate em áreas de supressão florestal. Belém: Brasil.

de Souza, P., Marendy, P., Barbosa, K., Budi, S., Hirsch, P., Nikolic, N., Gunthorpe, T. Pessin, G., Davie, A. (2018) “Low-Cost Electronic Tagging System for Bee Monitoring”, Sensors vol.18 2124. doi: 10.3390/s18072124

Filipiak, M. (2018) “A Better Understanding of Bee Nutritional Ecology Is Needed to Optimize Conservation Strategies for Wild Bees - The Application of Ecological Stoichiometry”, Insects, vol. 9, no. July, p. 1-13. doi: 10.3390/insects9030085

Giannini, T. C., Costa, W. F., Borges, R. C., Miranda L., Costa, C. P. W., Saraiva, A. M. e Fonseca, V. L. I. (2020) “Climate change in the Eastern Amazon: crop-pollinator and occurrence-restricted bees are potentially more affected”, Reg. Environ. Chang., vol. 20, p. 1-12. doi: https://doi.org/10.1007/s10113-020-01611-y

Gomes, P. A. B., Suhara, Y., Nunes-Silva, P., Costa, L., Arruda, H., Venturieri, G., Imperatriz-Fonseca, V. L., Pentland, A., Souza, P. e Pessin, G. (2020) “An Amazon stingless bee foraging activity predicted using recurrent artificial neural networks and attribute selection”, Nature research, vol. 10, pp. 1-12. doi: https://doi.org/10.1038/s41598-019-56352-8

Hallmann, C. A., Sorg, M., Jongejans, E., Siepel, H., Hofland, N., Schwan, H., Stenmans, W., Müller, A., Sumser, H., Hörren, T., Goulson, D. e de Kroon, H. (2017) “More than 75 percent decline over 27 years in total flying insect biomass in protected areas”, PLoS One, vol. 12, no. October, p. 18-22. doi: https://doi.org/10.1371/journal.pone.0185809

Júnior, T. D. C. and Rieder, R. (2020) “Automatic identification of insects from digital images: A survey”, Comput. Electron. Agric., vol. 178, no. April, p. 105784. doi: https://doi.org/10.1016/j.compag.2020.105784

Kuan, A. C., Grandi-Hoffman, G., Curry, R. J., Garber, K. V., Kanarek, A. R., Snyder, M. N., Wolfe, K. L. e Purucker, S. T. (2018) “Sensitivity analyses for simulating pesticide impacts on honey bee colonies”, Ecol. Modell., vol. 376, no. February, p. 15-27. doi: https://doi.org/10.1016/j.ecolmodel.2018.02.010

Liu, L., Wang, R., Xie, C., Yang, P., Wang, F., Surdiman, S. e Liu, W. (2019) “PestNet: An End-to-End Deep Learning Approach for Large-Scale Multi-Class Pest Detection and Classification”, IEEE Access, vol. 7, p. 45301-45312. doi: 10.1109/ACCESS.2019.2909522

Macharia, J. M., Gikungu, M. W., Karanja, R. e Okoth, S. (2020) “Managed bees as pollinators and vectors of bio control agent against grey mold disease in strawberry plantations”, African J. Agric. Res., vol. 16, no. 12, p. 1674-1680. doi: 10.5897/AJAR2020.15203

Marstaller, J., Tausch, F. e Stock, S. C. (2019) “DeepBees - Building and Scaling Convolutional Neuronal Nets For Fast and Large-Scale Visual Monitoring of Bee Hives”, in ICCV Workshop, October. doi: 10.1109/ICCVW.2019.00036

Pimentel, A. D. A., Absy, M. L., Rech, A. R. e de Abreu, V. H. R. (2020) “Pollen sources used by Frieseomelitta Ihering 1912 (Hymenoptera: Apidae: Meliponini) bees along the course of the Rio Negro, Amazonas, Brazil”, Acta Bot. Brasilica, vol. 34, no. June, p. 371-383. doi: 10.1590/0102-33062019abb0391

Qing, Y., Jin, F., Jian, T., Wei-gen, X., Xu-hua, Z., Bao-jun, Y., Jun, L., Yi-ze, X., Bo1, Y., Shu-zhen, W., Nai-yang, K. e Li-jun, W. (2020) “Development of an automatic monitoring system for rice light-trap pests based on machine vision”, J. Integr. Agric., vol. 19, no. February, p. 2500-2513. doi: 10.1016/S2095-3119(20)63168-9

Redmon, J. e Farhadi, A. (2016) “YOLO9000: Better, Faster, Stronger”, Cornell Univ., no. December. arXiv:1612.08242v1

Redmon, J. e Farhadi, A. (2018) “YOLOv3: An Incremental Improvement”, Cornell Univ., no. April. arXiv:1804.02767v1

Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2015) “You Only Look Once: Unified, Real-Time Object Detection”, Cornell Univ., no. May. arXiv:1506.02640v5

Sánchez-bayo, F. e Wyckhuys, K. A. G. (2019) “Worldwide decline of the entomofauna: A review of its drivers”, Biol. Conserv., vol. 232, no. September, p. 8-27. doi: https://doi.org/10.1016/j.biocon.2019.01.020

Shen, Y., Zhou, H., Li, J., Jian, F. e Jayas, D. S. (2018) “Detection of stored-grain insects using deep learning”, Comput. Electron. Agric., vol. 145, no. October, p. 319-325. doi: https://doi.org/10.1016/j.compag.2017.11.039

Xia, D., Chen, P., Wang, B., Zhang, J. e Xie, C. (2018) “Insect Detection and Classification Based on an Improved Convolutional Neural Network”, Sensors, vol. 18, no. November, p. 1-12. doi: 10.3390/s18124169