Intelligent Classification and Detection of Grains for Digital Agriculture in Corn Cultivation
Abstract
This work addresses the tasks of corn kernel classification and detection in images using state-of-the-art Deep Learning-based Computer Vision models. The goal is to enable the development of solutions for Digital Agriculture. In the classification task, it was observed that the imbalance of the classes had a low impact on the good performance of the models. In the detection task, it was possible to surpass results from the literature (a percentage increase of 16,33%) and also to assess the generalization in other scenarios. The results obtained contribute to the estimation of productivity and decision making in the context of corn cultivation.
References
CONAB (2024). Planilhas de custo de produção – milho. Disponível em [link]. Acesso em 25 de maio de 2024.
Cruz, J. C., Karam, D., Magalhães, P. C., and Monteiro, M. A. R. (2008). A Cultura do Milho. Embrapa.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255, Miami, FL, USA. IEEE.
Diwan, T., Anirudh, G., and Tembhurne, J. V. (2023). Object Detection Using YOLO: Challenges, Architectural Successors, Datasets and Applications. Multimed. Tools Appl., 82(6):9243–9275.
Embrapa (2014). Visão 2014–2034 – O Futuro do Desenvolvimento Tecnológico da Agricultura Brasileira (Síntese). Embrapa, Distrito Federal, Brasil.
Gillette, S., Yin, L., Kianian, P. M. A., Pawlowski, W. P., and Chen, C. (2023). Corn360: a method for quantification of corn kernels. Plant Methods, 19(1):23.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. The MIT Press, Cambridge.
Hobbs, J., Khachatryan, V., Anandan, B. S., Hovhannisyan, H., and Wilson, D. (2021). Broad dataset and methods for counting and localization of on-ear corn kernels. Front. Robot. AI, 8:627009.
Howard, A., S. M. Z. M. Z. A. and Chen, L.-C. . (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), page 4510–4520.
Jocher, G., Chaurasia, A., and Qiu, J. (2023). YOLOv8 – real-time object detection. Disponível em [link]. Acesso em 25 de maio de 2024.
Khaki, S., Pham, H., Han, Y., Kuhl, A., Kent, W., and Wang, L. (2020). Convolutional neural networks for image-based corn kernel detection and counting. Sensors (Basel), 20(9):2721.
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft COCO: Common Objects in Context. In Proceedings of the 13th European Conference on Computer Vision (ECVV 2014), pages 740–755, Suíça. Springer.
Michelucci, U. (2019). Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection. Apress, Suíça.
Miranda, R. A. d., Durães, F. O. M., Garcia, J. C., Parentoni, S., Santana, D. P., Purcino, A. C., and Alves, E. (2019). Supersafra de milho e o papel da tecnologia no aumento da produção. Revista de Política Agrícola, 28(2):149.
Pachouri, V., Pandey, S., Gehlot, A., Negi, P., Chhabra, G., and Joshi, K. (2023). Agriculture 4.0: Inculcation of big data and internet of things in sustainable farming. In 2023 IEEE International Conference on Contemporary Computing and Communications (InC4), volume 1, pages 1–4, Bangalore, India. IEEE.
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, Niterói, Brasil.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Estados Unidos. IEEE.
Rodrigues, V. d. N., Von Pinho, R. G., Paglis, C. M., Bueno Filho, J. S. d. S., and Brito, A. H. d. (2005). Comparação entre métodos para estimar a produtividade de grãos de milho. Ciênc. Agrotecnologia, 29(1):34–42.
Sasseron, J. C. (2013). Modelos matemáticos para previsão da produtividade do milho em dois sistemas de cultivo. Disponível em [link]. Acesso em 25 de maio de 2024.
Souza, A. E. d., Dos Reis, J. G. M., Raymundo, J. C., and Pinto, R. S. (2018). Estudo da produção do Milho no brasil. S. Am. Dev. Soc. J., 4(11):182.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, volume 1, pages 1–9, Massachusetts, Estados Unidos. IEEE.
Tan, M. and Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning, volume 97, pages 6105–6114.
Tang, S., Zhu, Q., Zhou, X., Liu, S., and Wu, M. (2002). A Conception of Digital Agriculture. In IEEE International Geoscience and Remote Sensing Symposium, pages 3026–3028, Canada. IEEE.
Cruz, J. C., Karam, D., Magalhães, P. C., and Monteiro, M. A. R. (2008). A Cultura do Milho. Embrapa.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255, Miami, FL, USA. IEEE.
Diwan, T., Anirudh, G., and Tembhurne, J. V. (2023). Object Detection Using YOLO: Challenges, Architectural Successors, Datasets and Applications. Multimed. Tools Appl., 82(6):9243–9275.
Embrapa (2014). Visão 2014–2034 – O Futuro do Desenvolvimento Tecnológico da Agricultura Brasileira (Síntese). Embrapa, Distrito Federal, Brasil.
Gillette, S., Yin, L., Kianian, P. M. A., Pawlowski, W. P., and Chen, C. (2023). Corn360: a method for quantification of corn kernels. Plant Methods, 19(1):23.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. The MIT Press, Cambridge.
Hobbs, J., Khachatryan, V., Anandan, B. S., Hovhannisyan, H., and Wilson, D. (2021). Broad dataset and methods for counting and localization of on-ear corn kernels. Front. Robot. AI, 8:627009.
Howard, A., S. M. Z. M. Z. A. and Chen, L.-C. . (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), page 4510–4520.
Jocher, G., Chaurasia, A., and Qiu, J. (2023). YOLOv8 – real-time object detection. Disponível em [link]. Acesso em 25 de maio de 2024.
Khaki, S., Pham, H., Han, Y., Kuhl, A., Kent, W., and Wang, L. (2020). Convolutional neural networks for image-based corn kernel detection and counting. Sensors (Basel), 20(9):2721.
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft COCO: Common Objects in Context. In Proceedings of the 13th European Conference on Computer Vision (ECVV 2014), pages 740–755, Suíça. Springer.
Michelucci, U. (2019). Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection. Apress, Suíça.
Miranda, R. A. d., Durães, F. O. M., Garcia, J. C., Parentoni, S., Santana, D. P., Purcino, A. C., and Alves, E. (2019). Supersafra de milho e o papel da tecnologia no aumento da produção. Revista de Política Agrícola, 28(2):149.
Pachouri, V., Pandey, S., Gehlot, A., Negi, P., Chhabra, G., and Joshi, K. (2023). Agriculture 4.0: Inculcation of big data and internet of things in sustainable farming. In 2023 IEEE International Conference on Contemporary Computing and Communications (InC4), volume 1, pages 1–4, Bangalore, India. IEEE.
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, Niterói, Brasil.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Estados Unidos. IEEE.
Rodrigues, V. d. N., Von Pinho, R. G., Paglis, C. M., Bueno Filho, J. S. d. S., and Brito, A. H. d. (2005). Comparação entre métodos para estimar a produtividade de grãos de milho. Ciênc. Agrotecnologia, 29(1):34–42.
Sasseron, J. C. (2013). Modelos matemáticos para previsão da produtividade do milho em dois sistemas de cultivo. Disponível em [link]. Acesso em 25 de maio de 2024.
Souza, A. E. d., Dos Reis, J. G. M., Raymundo, J. C., and Pinto, R. S. (2018). Estudo da produção do Milho no brasil. S. Am. Dev. Soc. J., 4(11):182.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, volume 1, pages 1–9, Massachusetts, Estados Unidos. IEEE.
Tan, M. and Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning, volume 97, pages 6105–6114.
Tang, S., Zhu, Q., Zhou, X., Liu, S., and Wu, M. (2002). A Conception of Digital Agriculture. In IEEE International Geoscience and Remote Sensing Symposium, pages 3026–3028, Canada. IEEE.
Published
2024-07-21
How to Cite
MENDONÇA, Arthur Uguen de; GUEDES, Elloá B..
Intelligent Classification and Detection of Grains for Digital Agriculture in Corn Cultivation. In: WORKSHOP ON COMPUTING APPLIED TO THE MANAGEMENT OF THE ENVIRONMENT AND NATURAL RESOURCES (WCAMA), 15. , 2024, Brasília/DF.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 1-10.
ISSN 2595-6124.
DOI: https://doi.org/10.5753/wcama.2024.1881.
