Research on Detection of Rice Pests and Diseases Based on Improved yolov5 Algorithm
Source abstract
Abstract
Rice pests and diseases have a significant impact on the quality and yield of rice, and even have a certain impact on and cause a loss in the national agricultural industry and economy. The timely and accurate detection of pests and diseases is the basic premise of formulating effective rice pest control and prevention programs. However, the complexity and diversity of pests and diseases and the high similarity between some pests and diseases make the detection and classification task of pests and diseases extremely difficult without detection tools. The existing target detection algorithms can barely complete the task of detecting pests and diseases, but the detection effect is not ideal. In the actual situation of rice disease and insect pest detection, the detection algorithm is required to have fast speed, high accuracy, and good performance for small target detection, and so this paper improved the popular yolov5 algorithm to achieve an ideal detection performance suitable for rice disease and insect pest detection. This paper briefly introduces the current status and influence of rice pests and diseases and several target detection algorithms based on deep learning. Based on the yolov5 algorithm, the RepVGG network structure is introduced, 3*3 convolution is combined with ReLU, a training time model with multi-branch topology is adopted, and the inference time is reduced through layer merging. To improve algorithm detection speed, the SK attention mechanism is introduced to improve the receptive field of the convolution kernel to obtain more information and improve accuracy. In addition, Adaptive NMS is replaced by Adaptive NMS, the dynamic suppression strategy is adopted, and scores for learning density are set, which greatly improves the problems of missing detection and the false detection of small targets. Finally, the improved algorithm model is combined with membrane calculation to further improve the accuracy and speed of the algorithm. According to the experimental results, the accuracy of the improved algorithm is increased by about 2.7 percentage points, and the mAP is increased by 4.3 percentage points, up to 94.4%. The speed is improved by about 2.8 percentage points, and indicators such as recall rate and AP are improved.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Food Supply Chain Traceability · Spectroscopy and Chemometric Analyses
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430040, China
School of Information Science and Technology, Chengdu University of Technology, Chengdu 610059, China
Funding
School Enterprise Cooperation Project · Hubei Provincial Teaching and Research Project · Ministry of Education Industry-University Cooperation Collaborative Education Project
References (32)
Show source-provided references
1. Yin, D., and Zhao, Y. (2023). Analysis of high-yield cultivation techniques of high quality rice and common pest control methods. Contemp. Agric. Mach., 4.
2. Application effect analysis of plant protection UAV in rice pest control
3. Damage symptoms and main control measures of rice diseases and insect pests in northern rice growing areas
4. Analysis on control technology of main diseases and insect pests in rice
5. Litchi pest detection model based on improved YOLO v4
6. Research on detection of coffee leaf pests and diseases based on YOLOv5
7. Detection method of diseases and insect pests of Guangfo hand based on improved SSD
8. Detection of plant diseases and insect pests based on visual enhanced attention model
9. Research on Detection and identification of maize leaf pests and diseases based on improved YOLOv3 model
10. Research on crop pest detection based on improved residual network
11. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
12. Roh, M.C., and Lee, J. (2017, January 8–12). Refining faster-RCNN for accurate object detection. Proceedings of the 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA), Nagoya, Japan.10.23919/MVA.2017.7986913 ↗
13. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst., 28.
14. Li, G., Song, Z., and Fu, Q. (2018, January 12–14). A new method of image detection for small datasets under the framework of YOLO network. Proceedings of the 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China.10.1109/IAEAC.2018.8577214 ↗
15. Ranjan, A., Pathare, N., Dhavale, S., and Kumar, S. (2022, January 26–28). Performance Analysis of YOLO Algorithms for Real-Time Crowd Counting. Proceedings of the 2022 2nd Asian Conference on Innovation in Technology (ASIANCON), Ravet, India.10.1109/ASIANCON55314.2022.9909018 ↗
16. A Study of YOLO Algorithm for Multi-target Detection
17. Wu, W., Liu, H., Li, L., Long, Y., Wang, X., Wang, Z., Li, J., and Chang, Y. (2021). Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image. PLoS ONE, 16.10.1371/journal.pone.0259283 ↗
18. Kim, J.H., Kim, N., Park, Y.W., and Won, C.S. (2022). Object detection and classification based on YOLO-V5 with improved maritime dataset. J. Mar. Sci. Eng., 10.10.3390/jmse10030377 ↗
19. Yao, J., Qi, J., Zhang, J., Shao, H., Yang, J., and Li, X. (2021). A real-time detection algorithm for Kiwifruit defects based on YOLOv5. Electronics, 10.10.3390/electronics10141711 ↗
20. Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., and Sun, J. (2021, January 20–25). Repvgg: Making vgg-style convnets great again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01352 ↗
21. Chu, X., Li, L., and Zhang, B. (2022). Make RepVGG Greater Again: A Quantization-aware Approach. arXiv.
22. Nergiz, M. (2021, January 15–17). Analysis of RepVGG on Small Sized Dandelion Images Dataset in terms of Transfer Learning, Regularization, Spatial Attention as well as Squeeze and Excitation Blocks. Proceedings of the 2021 6th International Conference on Computer Science and Engineering (UBMK), Ankara, Turkey.10.1109/UBMK52708.2021.9558941 ↗
23. Li, X., Wang, W., Hu, X., and Yang, J. (2019, January 16–17). Selective kernel networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00060 ↗
24. Multibranch selective kernel networks for hyperspectral image classification
25. Selective kernel networks for weakly supervised relation extraction10.1049/cit2.12008 ↗
26. Liu, S., Huang, D., and Wang, Y. (2019, January 15–20). Adaptive nms: Refining pedestrian detection in a crowd. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00662 ↗
27. Joint-attention feature fusion network and dual-adaptive NMS for object detection10.1016/j.knosys.2022.108213 ↗
28. Peng, H., Xu, H., Gao, Z., Tian, X., Deng, Q., and Xian, C. (2023). Detection method of crop pests in field based on improved YOLOF model. Trans. Chin. Soc. Agric. Mach., 54.
29. Research on tomato pest and disease recognition algorithm based on YOLO
30. Improved YOLOv4-GhostNet method for identification of rice pests and diseases
31. Cotton defect detection based on FS-YOLOv3 and multi-scale feature fusion
32. Apple object detection based on multi-scale and mixed attention mechanism