Research on rice disease recognition based on improved YOLOv5 algorithm

ZHOU Si-jie; LIU Tian-qi; CHEN Tian-hua

doi:10.13733/j.jcam.issn.2095-5553.2024.08.036

Journal of Chinese Agricultural Mechanization > 2024 > 45(8): 246-253. > DOI: 10.13733/j.jcam.issn.2095-5553.2024.08.036

ZHOU Si-jie, LIU Tian-qi, CHEN Tian-hua. Research on rice disease recognition based on improved YOLOv5 algorithm[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(8): 246-253. DOI: 10.13733/j.jcam.issn.2095-5553.2024.08.036

Citation:

PDF (3734 KB)

Research on rice disease recognition based on improved YOLOv5 algorithm

1. School of Artificial Intelligence, Beijing Technology and Business University;
2. School of E-business and logistics, Beijing Technology and Business University

More Information

Received Date: March 02, 2023

Graphical Abstract

Abstract

Abstract

In order to address the problem that traditional deep learning algorithms are difficult to identify rice diseases accurately and efficiently in complex environments, an improved YOLOv5 algorithm was proposed to detect the disease spots of common rice blight, rice blast, tungro disease and brown spot disease. A hybrid domain attention mechanism was combined with the original YOLOv5 algorithm for feature correction, which improved the model′s ability to determine the position of rice leaves and disease spot location. The original CIoU＿loss（Complete Intersection over Union） was replaced by SIoU＿loss（SCYLLA Intersection over Union） in the loss function part to compensate for the problem that CIoU＿loss did not focus on the angular offset of the bounding box and the Ground truth box. Soft-NMS（Soft Non Maximum Suppression） was chosen to filter the prediction boxes to alleviate the leakage caused by the overlapping area of different lesions in the conventional NMS. In the ablation experiment, the mAP（mean Average Presicion） of the improved algorithm reached 0. 884 in the rice disease identification task, which was 2. 9 percentage points higher than the original YOLOv5 algorithm, and the improvement was greater in the identification of brown spot. It proved the effectiveness of the improved YOLOv5 algorithm in the rice disease identification task.
- rice disease,
- YOLOv5 algorithm,
- attention mechanism,
- object detection

FullText(HTML)

References (20)

References

[1]	亓璐,张涛,曾娟,等.近年我国水稻五大产区主要病害发生情况分析[J].中国植保导刊,2021, 41(4):37-42, 65. Qi Lu, Zhang Tao, Zeng Juan, et al. Analysis of the occurrence and control of diseases in five major rice-producing areas in China in recent years[J]. China Plant Protection, 2021, 41(4), 37-42, 65.
[2]	田有文,王立地,姜淑华.基于图像处理和支持向量机的玉米病害识别[J].仪器仪表学报,2006, 27(6):2123-2124.
[3]	张建华,祁力钧,冀荣华,等.基于粗糙集和BP神经网络的棉花病害识别[J].农业工程学报,2012, 28(7):161-167. Zhang Jianhua, Qi Lijun, Ji Ronghua, et al. Cotton diseases identification based on rough sets and BP neural network[J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(7):161-167.
[4]	Omrani E, Khoshnevisan B, Shamshirband S, et al.Potential of radial basis function-based support vector regression for apple disease detection[J]. Measurement,2014, 55:512-519.
[5]	Wang H, Li G, Ma Z, et al. Image recognition of plant diseases based on backpropagation networks[C]. 2012 5th International Congress on Image and Signal Processing.IEEE, 2012:894-900.
[6]	Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J].Communications of the ACM, 2017, 60(6):84-90.
[7]	刘阗宇,冯全,杨森.基于卷积神经网络的葡萄叶片病害检测方法[J].东北农业大学学报,2018, 49(3):73-83. Liu Tianyu, Feng Quan, Yang Sen. Detecting grape diseases based on convolutional neural network[J]. Journal of Northeast Agricultural University, 2018, 49(3):73-83.
[8]	孙丰刚,王云露,兰鹏,等.基于改进YOLOv5s和迁移学习的苹果果实病害识别方法[J].农业工程学报,2022,38(11):171-179. Sun Fenggang, Wang Yunlu, Lan Peng, et al.Identification of apple fruit diseases using improved YOLOv5s and transfer learning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(11):171-179.
[9]	Sanyal P, Patel S C. Pattern recognition method to detect two diseases in rice plants[J]. The Imaging Science Journal, 2008, 56(6):319-325.
[10]	Lu Y, Yi S, Zeng N, et al. Identification of rice diseases using deep convolutional neural networks[J].Neurocomputing, 2017, 267:378-384.
[11]	万颖,杨红云,王映龙,等.基于图像分割与卷积神经网络的水稻病害识别[J].西北农业学报,2022, 31(2):246-256.
[12]	Redmon J, Divvala S, Girshick R, et al. You only look once:Unified, real-time object detection[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:779-788.
[13]	Redmon J, Farhadi A. YOLOv3:An incremental improvement[J]. Computer Vision and Pattern Recognition, 2018, 87(8):101-104.
[14]	Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4:Optimal speed and accuracy of object detection[J]. Computer Vision and Pattern Recognition, 2020, 57(5):9-12.
[15]	Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]. Proceedings of the IEEE conference on Computer Cision and Pattern Recognition,2017:2117-2125.
[16]	Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018:8759-8768.
[17]	Woo S, Park J, Lee J Y, et al. Cbam:Convolutional block attention module[C]. Proceedings of the European Conference on Computer Vision, 2018:3-19.
[18]	Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C].Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2018:7132-7141.
[19]	Gevorgyan Z. SIoU loss:More powerful learning for bounding box regression[J]. arXiv preprint arXiv:2205. 12740, 2022.
[20]	Bodla N, Singh B, Chellappa R, et al. Soft-NMS:Improving object detection with one line of code[C].Proceedings of the IEEE International Conference on Computer vision, 2017:5561-5569.