Embedded neural networks for identifying Spodoptera frugiperda in corn plantations

• Bianca Soares UFC
• Wendell Silva UFC
• Gabriela Ponciano UFC
• Bruna Stefanie UFC
• Valentine Almeida UFC
• Patrick Pastori UFGD
• Deborah Magalhães Unilab
• Atslands Rocha UFC

DOI: https://doi.org/10.5753/eniac.2024.244552

Abstract

The Spodoptera frugiperda is one of the most important pests in global agriculture. Its monitoring typically requires visual inspection and manual counting of individuals. However, advances in computer vision, machine learning, and the Internet of Things offer ways to achieve fast and accurate monitoring. In this scenario, we investigated the use of lightweight convolutional neural networks and dense networks to extract relevant features from images of these insects captured in traps. The best extraction models, MobileNet and DenseNet201, were combined with MLP and achieved classification accuracies of 0.89 and 0.94, respectively, when deployed on a Raspberry Pi. Our results show that DenseNet201 offers higher accuracy than MobileNet. Nevertheless, MobileNet is more efficient in processing and has a shorter execution time. Therefore, it emerges as a viable alternative for identifying Spodoptera frugiperda in the field with computationally constrained devices. Finally, this work contributes directly to the automated and precise monitoring of crop pests.

Keywords: Pest monitoring, Computer vision, Embedded AI, Deep learning

References

Azfar, S., Nadeem, A., Ahsan, K., Mehmood, A., Almoamari, H., and Alqahtany, S. S. (2023). Iot-based cotton plant pest detection and smart-response system. Applied Sciences, 13(3):1851.

Bechar, M. E. A., Settouti, N., Daho, M. E. H., Adel, M., and Chikh, M. A. (2019). Influence of normalization and color features on super-pixel classification: application to cytological image segmentation. Australasian physical & engineering sciences in medicine, 42:427–441.

FAO (2022). Faostat: Crops and livestock products. Accessed: 2024-07-30.

Gallo, D., Nakano, O., Silveira Neto, S., Carvalho, R., Baptista, C., Berti Filho, E., Parra, J., Zucchi, R., Alves, S., Vendramim, J., et al. (2002a). Agricultural entomology= entomologia agrícola. fealq, piracicaba, sp, brazil.

Gallo, D., Nakano, O., Silveira Neto, S. S., Carvalho, R. P. L., Batista, G. C., Filho, E. B., P., P. J. R., Zucchi, R. A., Alves, S. B., Vendramim, J. D., Marchini, L. C., Lopes, J. R. S., and Omoto, C. (2002b). Entomologia agrícola. FEALQ, Piracicaba.

Ghazal, S., Munir, A., and Qureshi, W. S. (2024). Computer vision in smart agriculture and precision farming: Techniques and applications. Artificial Int. in Agriculture.

Guo, Q., Wang, C., Xiao, D., and Huang, Q. (2024). A lightweight open-world pest image classifier using resnet8-based matching network and nt-xent loss function. Expert Systems with Applications, 237:121395.

Hassan, S. I., Alam, M. M., Illahi, U., and Suud, M. M. (2023). A new deep learning-based technique for rice pest detection using remote sensing. PeerJ Computer Science, 9:e1167.

Hu, T., Zhang, X., Khanal, S., Wilson, R., Leng, G., Toman, E. M., Wang, X., Li, Y., and Zhao, K. (2024). Climate change impacts on crop yields: A review of empirical findings, statistical crop models, and machine learning methods. Environmental Modelling & Software, page 106119.

Jiang, S., Luo, B., Jiang, H., Zhou, Z., and Sun, S. (2024). Research on dense object detection methods in congested environments of urban streets and roads based on dcyolo. Scientific Reports, 14(1):1127.

Junior, T. D. C. and Rieder, R. (2020). Uma implementação baseada em mask r-cnn para detecção de insetos em imagens digitais. Rev. Bras. de Entomologia, 64(2):149–157.

Karunathilake, E., Le, A. T., Heo, S., Chung, Y. S., and Mansoor, S. (2023). The path to smart farming: Innovations and opportunities in precision agriculture. Agriculture, 13(8):1593.

Kathole, A. B., Katti, J., Lonare, S., and Dharmale, G. (2023). Identify and classify pests in the agricultural sector using metaheuristics deep learning approach. Franklin Open, 3(1):100024.

Kenis, M., Benelli, G., Biondi, A., Calatayud, P.-A., Day, R., Desneux, N., Harrison, R. D., Kriticos, D., Rwomushana, I., van den Berg, J., et al. (2022). Invasiveness, biology, ecology, and management of the fall armyworm, spodoptera frugiperda. Entomologia Generalis.

Mira, J. L., Gómez, S., del Río, A., Díaz, F., Lozano, M., and García, L. (2024). Benchmarking of computer vision methods for energy-efficient high-accuracy olive fly detection on edge devices. Multimedia Tools and Applications, 83(1):1203–1220.

Montezano, D. G., Sosa-Gómez, D., Specht, A., Roque-Specht, V. F., Sousa-Silva, J. C., Paula-Moraes, S. d., Peterson, J. A., and Hunt, T. (2018). Host plants of s. frugiperda (lepidoptera: Noctuidae) in the americas. African entomology, 26(2):286–300.

Muhammed, D., Ahvar, E., Ahvar, S., Trocan, M., Montpetit, M.-J., and Ehsani, R. (2024). Artificial Intelligence of Things (AIoT) for smart agriculture: A review of architectures, technologies and solutions. Journal of Network and Computer Applications, 228:103905.

Ngugi, H. N., Ezugwu, A. E., Akinyelu, A. A., and Abualigah, L. (2024). Revolutionizing crop disease detection with computational deep learning: a comprehensive review. Environmental Monitoring and Assessment, 196(3):302.

Nixon, M. S. and Aguado, A. S. (2020). Image processing. In Feature Extraction and Image Processing for Computer Vision, pages 83–139. Elsevier.

Obasekore, H., Fanni, M., Ahmed, S. M., Parque, V., and Kang, B.-Y. (2023). Agricultural robot-centered recognition of early-developmental pest stage based on deep learning: A case study on fall armyworm (spodoptera frugiperda). Sensors, 23(6):3147.

Palei, S., Lenka, R. K., Nayak, S. S., Mohanty, R., Jena, B., and Saxena, S. (2023). Precision Agriculture: ML and DL-Based Detection and Classification of Agricultural Pests. In 2023 2nd International Conference on Ambient Intelligence in Health Care (ICAIHC), pages 1–6, Bhubaneswar, India. IEEE.

Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115:211–252.

Silva, W. d. S., Soares, B., Almeida, V. d. L., Viana, L., Pastori, P. L., Magalhaes, D. M., and da Rocha, A. R. (2024). Detecçao da praga spodoptera frugiperda no cultivo de milho usando armadilhas inteligentes e visao computacional. In Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais (WCAMA), pages 61–70. SBC.

Yodrot, T., Sutacha, C., Orachon, T., Jangjongdee, N., and Boonyasuwanno, S. (2024). A Study on the Potency of Hybrid Models: Detecting Diseases in Cucumber Leaves with Pre-trained CNNs and SVM. In 2024 12th International Electrical Engineering Congress (iEECON), pages 1–4, Pattaya, Thailand. IEEE.

Yu, D., Xu, Q., Guo, H., Zhao, C., Lin, Y., and Li, D. (2020). An efficient and lightweight convolutional neural network for remote sensing image scene classification. Sensors, 20(7):1999.