Otimização de Modelos de Aprendizado de Máquina para Detecção de Pragas via Imagens Agrícolas com Eficiência Energética e de Memória
Resumo
A otimização de modelos de aprendizado de máquina para contagem automática de pragas através de imagens, em dispositivos com recursos limitados, viabiliza a disseminação dessa tecnologia em campos agrícolas. Neste trabalho, investigam-se técnicas de compressão de modelos para um sistema de detecção de pragas embarcado em dispositivos de baixo custo. Os resultados indicam que as técnicas de compressão avaliadas têm impacto pouco significativo na acurácia do modelo YOLO, permitindo sua execução com menor consumo de memória e energia, sem perda relevante na confiabilidade das predições. A validação do modelo em sistema embarcado demonstrou redução de 14% do consumo energético, mantendo a acurácia do modelo quase constante.Referências
Aaron, A., Hassan, M., Hamada, M., and Kakudi, H. (2023). A lightweight deep learning model for identifying weeds in corn and soybean using quantization. Engineering Proceedings, 56(1):318.
Abbas, M., Saleem, M., Hussain, D., Ramzan, M., Jawad Saleem, M., Abbas, S., Hussain, N., Irshad, M., Hussain, K., Ghouse, G., et al. (2022). Review on integrated disease and pest management of field crops. International Journal of Tropical Insect Science, 42(5):3235–3243.
Ahmad, S., Shakeel, I., Mehfuz, S., and Ahmad, J. (2023). Deep learning models for cloud, edge, fog, and iot computing paradigms: Survey, recent advances, and future directions. Computer Science Review, 49:100568.
Altaie, U. K., Abdelkareem, A. E., and Alhasanat, A. (2025). Lightweight optimization of yolo models for resource-constrained devices: A comprehensive review. Diyala Journal of Engineering Sciences, 18(4):1–26.
Bouri, M., Arslan, K. S., and Şahin, F. (2023). Climate-smart pest management in sustainable agriculture: Promises and challenges. Sustainability, 15(5):4592.
Ediagbonya, T. F., Areo, I. O., Mupenzi, C., Mind’je, R., Kamuhanda, J. K., and Kabano, S. (2025). Reduced pesticide dependency through crop management. Discover Applied Sciences, 7(7):776.
He, H.-m., Liu, L.-n., Munir, S., Bashir, N. H., Yi, W., Jing, Y., and Li, C.-y. (2019). Crop diversity and pest management in sustainable agriculture. Journal of Integrative Agriculture, 18:1945–1952.
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, 13:1593.
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. Schweizerbart Science Publishers.
Leybourne, D. J., Musa, N., and Yang, P. (2025). Can artificial intelligence be integrated into pest monitoring schemes to help achieve sustainable agriculture? an entomological, management and computational perspective. Agricultural and Forest Entomology, 27(1):8–17.
Lin, Y., Xia, Y., Xia, P., Liu, Z., Wang, H., Qin, C., Gong, L., and Liu, C. (2025). Yolo11araf: An accurate and lightweight method for apple detection in real-world complex orchard environments. Agriculture, 15(10):1104.
Overton, K., Maino, J. L., Day, R., Umina, P. A., Bett, B., Carnovale, D., Ekesi, S., Meagher, R., and Reynolds, O. L. (2021). Global crop impacts, yield losses and action thresholds for fall armyworm (Spodoptera frugiperda): A review. Crop Protection, 145:105641.
Preti, M., Verheggen, F., and Angeli, S. (2021). Insect pest monitoring with camera-equipped traps: strengths and limitations. Journal of pest science, 94(2):203–217.
Rai, N., Zhang, Y., Villamil, M., Howatt, K., Ostlie, M., and Sun, X. (2024). Agricultural weed identification in images and videos by integrating optimized deep learning architecture on an edge computing technology. Computers and Electronics in Agriculture, 216:108442.
Sayyad, J., Attarde, K., and Almustafa, K. M. (2025). A systematic literature review on deep learning approaches for small object detection. Array, page 100615.
Sharma, R., Sharma, B. B., et al. (2025). Design and implementation of real-time tomato plant growth monitoring system using deep learning based yolo and raspberry pi. Applied Artificial Intelligence.
Silva, W., Soares, B., Almeida, V., Viana, L., Pastori, P., Magalhães, D., and Rocha, A. (2024). Detecção da praga spodoptera frugiperda no cultivo de milho usando armadilhas inteligentes e visão computacional. In Anais do XV Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 61–70, Porto Alegre, RS, Brasil. SBC.
Stenberg, J. A. (2017). A conceptual framework for integrated pest management. Trends in Plant Science, 22:759–769.
Velten, S., Leventon, J., Jager, N., and Newig, J. (2015). What is sustainable agriculture? A systematic review. Sustainability, 7:7833–7865.
Wang, C., Han, Y., Yang, C., Wu, M., Chen, Z., Yun, L., and Jin, X. (2025). Cf-yolo for small target detection in drone imagery based on yolov11 algorithm. Scientific reports, 15(1):16741.
Wang, M. et al. (2023). Q-yolo: Efficient inference for real-time object detection. Pattern Recognition (ACPR 2023), 14408.
Abbas, M., Saleem, M., Hussain, D., Ramzan, M., Jawad Saleem, M., Abbas, S., Hussain, N., Irshad, M., Hussain, K., Ghouse, G., et al. (2022). Review on integrated disease and pest management of field crops. International Journal of Tropical Insect Science, 42(5):3235–3243.
Ahmad, S., Shakeel, I., Mehfuz, S., and Ahmad, J. (2023). Deep learning models for cloud, edge, fog, and iot computing paradigms: Survey, recent advances, and future directions. Computer Science Review, 49:100568.
Altaie, U. K., Abdelkareem, A. E., and Alhasanat, A. (2025). Lightweight optimization of yolo models for resource-constrained devices: A comprehensive review. Diyala Journal of Engineering Sciences, 18(4):1–26.
Bouri, M., Arslan, K. S., and Şahin, F. (2023). Climate-smart pest management in sustainable agriculture: Promises and challenges. Sustainability, 15(5):4592.
Ediagbonya, T. F., Areo, I. O., Mupenzi, C., Mind’je, R., Kamuhanda, J. K., and Kabano, S. (2025). Reduced pesticide dependency through crop management. Discover Applied Sciences, 7(7):776.
He, H.-m., Liu, L.-n., Munir, S., Bashir, N. H., Yi, W., Jing, Y., and Li, C.-y. (2019). Crop diversity and pest management in sustainable agriculture. Journal of Integrative Agriculture, 18:1945–1952.
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, 13:1593.
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. Schweizerbart Science Publishers.
Leybourne, D. J., Musa, N., and Yang, P. (2025). Can artificial intelligence be integrated into pest monitoring schemes to help achieve sustainable agriculture? an entomological, management and computational perspective. Agricultural and Forest Entomology, 27(1):8–17.
Lin, Y., Xia, Y., Xia, P., Liu, Z., Wang, H., Qin, C., Gong, L., and Liu, C. (2025). Yolo11araf: An accurate and lightweight method for apple detection in real-world complex orchard environments. Agriculture, 15(10):1104.
Overton, K., Maino, J. L., Day, R., Umina, P. A., Bett, B., Carnovale, D., Ekesi, S., Meagher, R., and Reynolds, O. L. (2021). Global crop impacts, yield losses and action thresholds for fall armyworm (Spodoptera frugiperda): A review. Crop Protection, 145:105641.
Preti, M., Verheggen, F., and Angeli, S. (2021). Insect pest monitoring with camera-equipped traps: strengths and limitations. Journal of pest science, 94(2):203–217.
Rai, N., Zhang, Y., Villamil, M., Howatt, K., Ostlie, M., and Sun, X. (2024). Agricultural weed identification in images and videos by integrating optimized deep learning architecture on an edge computing technology. Computers and Electronics in Agriculture, 216:108442.
Sayyad, J., Attarde, K., and Almustafa, K. M. (2025). A systematic literature review on deep learning approaches for small object detection. Array, page 100615.
Sharma, R., Sharma, B. B., et al. (2025). Design and implementation of real-time tomato plant growth monitoring system using deep learning based yolo and raspberry pi. Applied Artificial Intelligence.
Silva, W., Soares, B., Almeida, V., Viana, L., Pastori, P., Magalhães, D., and Rocha, A. (2024). Detecção da praga spodoptera frugiperda no cultivo de milho usando armadilhas inteligentes e visão computacional. In Anais do XV Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 61–70, Porto Alegre, RS, Brasil. SBC.
Stenberg, J. A. (2017). A conceptual framework for integrated pest management. Trends in Plant Science, 22:759–769.
Velten, S., Leventon, J., Jager, N., and Newig, J. (2015). What is sustainable agriculture? A systematic review. Sustainability, 7:7833–7865.
Wang, C., Han, Y., Yang, C., Wu, M., Chen, Z., Yun, L., and Jin, X. (2025). Cf-yolo for small target detection in drone imagery based on yolov11 algorithm. Scientific reports, 15(1):16741.
Wang, M. et al. (2023). Q-yolo: Efficient inference for real-time object detection. Pattern Recognition (ACPR 2023), 14408.
Publicado
19/07/2026
Como Citar
SILVA, Douglas; ESTEBAN, Matheus A.; SOARES, Bianca; SANTOS, Wendell; MAGALHÃES, Deborah; ROCHA, Atslands R..
Otimização de Modelos de Aprendizado de Máquina para Detecção de Pragas via Imagens Agrícolas com Eficiência Energética e de Memória. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO UBÍQUA E PERVASIVA (SBCUP), 18. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 328-338.
ISSN 2595-6183.
DOI: https://doi.org/10.5753/sbcup.2026.23934.
