Leaf Detection Using YOLOv4 for Phytopathogenic Diagnosis

  • Alfredo Felipe Lopes Neto Universidade Federal Rural do Semi-Árido
  • Araken de Medeiros Santos Universidade Federal Rural do Semi-Árido
  • Silvio Fernandes Universidade Federal Rural do Semi-Árido

Resumo


Devido ao impacto que as doenças em plantas causam na produção agrícola, é necessário meios de detectar os fitopatógenos de forma automatizada e eficaz para economizar tempo e recursos. Assim, este artigo apresenta o primeiro módulo de sistema para auxiliar na detecção de fitopatógenos em folhas de plantas de seis espécies diferentes. Tal módulo objetiva detectar folhas e gerar imagens individuais de cada folha a partir da imagem original. As imagens individuais geradas serão usadas para classificação individual de doenças das folhas para em seguida criar um contexto de classificação nos próximos módulos do sistema. O módulo de detecção apresentado neste artigo foi implementado usando a arquitetura YOLOv4. Os resultados indicam precisão de quase 90% e mAP de 91,27%, com resultados igualmente importantes nas métricas, recall e IoU.

Palavras-chave: Aprendizagem profunda, Yolov4, Detecção de doenças de plantas, Rede neural convolucional

Referências

Abinaya, N. S., Susan, D. and Sidharthan, R. K. (jun 2022). Deep learning-based segmental analysis of fish for biomass estimation in an occulted environment. Computers and Electronics in Agriculture, v. 197, p. 106985.

Agarwal, M., Singh, A., Arjaria, S., Sinha, A. and Gupta, S. (2020). ToLeD: Tomato Leaf Disease Detection using Convolution Neural Network. Procedia Computer Science, v. 167, p. 293–301.

Ahmad, M., Abdullah, M., Moon, H. and Han, D. (2021). Plant Disease Detection in Imbalanced Datasets Using Efficient Convolutional Neural Networks With Stepwise Transfer Learning. IEEE Access, v. 9, p. 140565–140580.

Aragão, A. and Contini, E. (2022). O agro no Brasil e no Mundo: uma síntese do período de 2000 a 2021. [link], [accessed on Jun 19].

Bochkovskiy, A., Wang, C.-Y. and Liao, H.-Y. M. (22 apr 2020). YOLOv4: Optimal Speed and Accuracy of Object Detection.

Chairma, L., B, P., G, S., et al. (2 feb 2023). Yolo for Detecting Plant Diseases. In 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS). . IEEE. [link].

Degadwala, S., Vyas, D., Chakraborty, U., Dider, A. R. and Biswas, H. (25 mar 2021). Yolo-v4 Deep Learning Model for Medical Face Mask Detection. In 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS). . IEEE.

Geetharamani, G. and J, A. P. (jun 2019). Identification of plant leaf diseases using a nine-layer deep convolutional neural network. Computers & Electrical Engineering, v. 76, p. 323–338.

Jocher, G., Nishimura, K., Mineeva, T. and Vilariño, R. (2020). Yolov5.

Kovács, Z. L. (2006). Redes neurais artificiais. 4. ed. São Paulo: Editora Livraria da Física.

Moupojou, E., Tagne, A., Retraint, F., et al. (2023). FieldPlant: A Dataset of Field Plant Images for Plant Disease Detection and Classification With Deep Learning. IEEE Access, v. 11, p. 35398–35410.

Nanehkaran, Y. A., Zhang, D., Chen, J., Tian, Y. and Al-Nabhan, N. (4 sep 2020). Recognition of plant leaf diseases based on computer vision. Journal of Ambient Intelligence and Humanized Computing,

Pappa, G. L. and Freitas, A. (2010). Automating the Design of Data Mining Algorithms. Berlin, Heidelberg: Springer Berlin Heidelberg.

Ponnusamy, V., Coumaran, A., Shunmugam, A. S., Rajaram, K. and Senthilvelavan, S. (jul 2020). Smart Glass: Real-Time Leaf Disease Detection using YOLO Transfer Learning. In 2020 International Conference on Communication and Signal Processing (ICCSP). . IEEE.

Rahimzadeh, M., Attar, A. and Sakhaei, S. M. (jul 2021). A fully automated deep learning-based network for detecting COVID-19 from a new and large lung CT scan dataset. Biomedical Signal Processing and Control, v. 68, p. 102588.

Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (8 jun 2015). You Only Look Once: Unified, Real-Time Object Detection.

Rezatofighi, H., Tsoi, N., Gwak, J., et al. (jun 2019). Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). . IEEE.

Skalski, P. (2019). Make Sense.

Susa, J. A. B., Nombrefia, W. C., Abustan, A. S., Macalisang, J. and Maaliw, R. R. (28 apr 2022). Deep Learning Technique Detection for Cotton and Leaf Classification Using the YOLO Algorithm. In 2022 International Conference on Smart Information Systems and Technologies (SIST). . IEEE.

UNEP (2021). How to Feed the World in 2050. [link]., [accessed on Jun 19].

Wu, D., Lv, S., Jiang, M. and Song, H. (nov 2020). Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments. Computers and Electronics in Agriculture, v. 178, p. 105742.

Yang, B., Gao, Z., Gao, Y. and Zhu, Y. (12 jun 2021). Rapid Detection and Counting of Wheat Ears in the Field Using YOLOv4 with Attention Module. Agronomy, v. 11, n. 6, p. 1202.

Yu, J. and Zhang, W. (8 may 2021). Face Mask Wearing Detection Algorithm Based on Improved YOLO-v4. Sensors, v. 21, n. 9, p. 3263.

Zhang, Q., Men, X., Hui, C., Ge, F. and Ouyang, F. (mar 2022). Wheat yield losses from pests and pathogens in China. Agriculture, Ecosystems & Environment, v. 326, p. 107821.

Zhao, S., Zhang, S., Lu, J., et al. (jul 2022). A lightweight dead fish detection method based on deformable convolution and YOLOV4. Computers and Electronics in Agriculture, v. 198, p. 107098.

Zheng, Z., Wang, P., Liu, W., et al. (19 nov 2019). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression.

Zheng, Z., Wang, P., Liu, W., et al. (3 apr 2020). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence, v. 34, n. 07, p. 12993–13000.
Publicado
25/09/2023
LOPES NETO, Alfredo Felipe; SANTOS, Araken de Medeiros; FERNANDES, Silvio. Leaf Detection Using YOLOv4 for Phytopathogenic Diagnosis. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 20. , 2023, Belo Horizonte/MG. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 866-879. ISSN 2763-9061. DOI: https://doi.org/10.5753/eniac.2023.234502.