Biosystems Engineering and Renewable Energies

A multidisciplinary Journal in the field of Agricultural Engineering

Current Issue

By Issue

By Author

By Subject

Author Index

Keyword Index

About Journal

Aims and Scope

Editorial Board

Publication Ethics

Indexing and Abstracting

Related Links

FAQ

Peer Review Process

Journal Metrics

News

Weeds detection in saffron fields using an improved YOLOv5 model

Document Type : Original Article

Authors

1 Department of Biosystem Engineering, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan,

2 Department of Biosystem Engineering, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran

Abstract

The excessive use of agricultural pesticides and inputs has caused severe environmental damage to agricultural ecosystems. By applying digital agriculture and variable rate application systems, various sections of a farm can be managed with varying levels of pesticides and inputs, which is beneficial both in terms of production costs and environmental issues. In this study, a weed and saffron plant detection model was designed and evaluated to develop a selective weed control system in saffron fields. The proposed weed detection model is based on the Yolov5 object detection model. Several CBS and C3 modules in the Yolov5s model were replaced with Ghost Bottleneck and C3Ghost modules, respectively. This was done to reduce the number of model parameters and make the network lighter, which increases the speed of image processing during model training and inference. Furthermore, to improve the detection accuracy of the proposed model, a coordinate attention (CoordAtt) layer was used. The results showed that the number of parameters in the proposed model was reduced by 47% compared to the corresponding model in terms of network width and depth coefficients in Yolov5 versions. Meanwhile, among the six trained models, the modified Yolov5s model demonstrated the best performance, achieving accuracy and recall values equal to 81% and 67%, respectively. The detection accuracy of the proposed model was 3.93% higher than that of the best-performing Yolov5 algorithm. Due to the lightweight nature of the proposed algorithm, it can be used for real-time weed detection in agricultural fields to develop selective control systems.

Highlights

Research Highlights:

  • A novel weed detection model based on YOLOv5 is proposed to improve efficiency and accuracy in saffron fields.
  • The model utilizes innovative techniques like Ghost Bottleneck and C3Ghost modules to reduce computational complexity and enhance speed.
  • The incorporation of a coordinate attention layer significantly improves the model's ability to accurately detect weeds in challenging field conditions.
  • The proposed model offers a promising solution for selective weed control, leading to reduced pesticide usage and environmental impact.

Keywords

References
Abdullaev, F. I. & Frenkel, G. D. (1999). Saffron in biological and medical research. Saffron: Crocus Sativus L, 103–113.
Adhinata, F. D. & Sumiharto, R. (2024). A comprehensive survey on weed and crop classification using machine learning and deep learning. Artificial Intelligence in Agriculture, 13, 45-63.
Admasu, G., Haji, J., Siyum, C., & Ndemo, E. (2024). Impact of Climate Change Adaptation Strategies on Food Security of Farm Households in Rural Dire Dawa Administration, Ethiopia. Sustainable Agriculture Research, 13(2), 1-15.
Alif, M. A. R. & Hussain, M. (2024). YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain. ArXiv Preprint.
Cheng, B., & Matson, E. T. (2015). A feature-based machine learning agent for automatic rice and weed discrimination. International Conference on Artificial Intelligence and Soft Computing, 517–527.
Fernández, J.-A. (2004). Biology, biotechnology and biomedicine of saffron.
Guerrero, J. M., Ruz, J. J. & Pajares, G. (2017). Crop rows and weeds detection in maize fields applying a computer vision system based on geometry. Computers and Electronics in Agriculture, 142, 461–472.
Hamuda, E., Glavin, M., & Jones, E. (2016). A survey of image processing techniques for plant extraction and segmentation in the field. Computers and Electronics in Agriculture, 125, 184–199.
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020). Ghostnet: More features from cheap operations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1580–1589.
Hou, Q., Zhou, D., & Feng, J. (2021). Coordinate attention for efficient mobile network design. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13713–13722.
Jeanmart, S., Edmunds, A. J. F., Lamberth, C., & Pouliot, M. (2016). Synthetic approaches to the 2010–2014 new agrochemicals. Bioorganic & Medicinal Chemistry, 24(3), 317–341.
José Bagur, M., Alonso Salinas, G. L., Jiménez-Monreal, A. M., Chaouqi, S., Llorens, S., Martínez-Tomé, M., & Alonso, G. L. (2017). Saffron: An old medicinal plant and a potential novel functional food. Molecules, 23(1), 30.
Kumar, P., & Misra, U. (2024). Deep Learning for Weed Detection: Exploring YOLO V8 Algorithm’s Performance in Agricultural Environments. 2024 2nd International Conference on Disruptive Technologies (ICDT), 255–258.
Kumar, R., Singh, V., Devi, K., Sharma, M., Singh, M. K., & Ahuja, P. S. (2008). State of art of saffron (Crocus sativus L.) agronomy: A comprehensive review. Food Reviews International, 25(1), 44–85.
Ministry of Agriculture-Jihad. (2020). Agricultural Statistics, (Vol. II). The Islamic Republic of Iran, Ministry of Agriculture-Jihad, Press. (In Persian).
Narayana, C. L., & Ramana, K. V. (2023). An efficient real-time weed detection technique using YOLOv7. International Journal of Advanced Computer Science and Applications, 14(2).
Peng, M., Zhang, W., Li, F., Xue, Q., Yuan, J., & An, P. (2023). Weed detection with improved YOLO v7. EAI Endorsed Transactions on Internet of Things, 9(3), e1. 
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779-788.
Rodrigo, M. A., Oturan, N., & Oturan, M. A. (2014). Electrochemically assisted remediation of pesticides in soils and water: a review. Chemical Reviews, 114(17), 8720–8745.
Shahnoushi, N., Abolhassani, L., Kavakebi, V., Reed, M., & Saghaian, S. (2020). Economic analysis of saffron production. In Saffron (pp. 337–356). Elsevier.
Singh, A., Ganapathysubramanian, B., Singh, A. K., & Sarkar, S. (2016). Machine learning for high-throughput stress phenotyping in plants. Trends in Plant Science, 21(2), 110–124.
Sonawane, S., & Patil, N. N. (2024). Deep learning-based weed detection in sesame crops using modified YOLOv5 model. Indian Journal of Weed Science, 56, 194-199.
Woyessa, D. (2022). Weed control methods used in agriculture. American Journal of Life Science and Innovation, 1(1), 19–26.
Zhou, X., Chen, T., & Zhang, B. (2023). Research on the impact of digital agriculture development on agricultural green total factor productivity. Land, 12(1), 195.
Biosystems Engineering and Renewable Energies
Volume 1, Issue 1
January 2025
Pages 44-50
Files
Share
How to cite
Statistics