Research on the Method of Crop Pest and Disease Recognition Based on the Improved YOLOv7-U-Net Combined Network
Source abstract
Abstract
This paper proposes an improved YOLOv7-U-Net combined network for crop pest and disease recognition, aiming to address the issue of insufficient accuracy in existing methods. For the YOLOv7 network, a self-attention mechanism is integrated into the SPPCSPC module to dynamically adjust channel weights and suppress redundant information while optimizing the PAFPN structure to enhance cross-scale feature fusion and improve small-object detection capabilities. For the U-Net network, the CBAM attention module is added before decoder skip connections, and depth-separable convolutions replace traditional kernels to strengthen feature fusion and detail attention. Experimental results show the improved algorithm achieves 97.49% detection accuracy, with mean average precision (mAP) reaching 96.91% and detection speed increasing to 90.41 FPS. The loss function of the improved U-Net network decreases towards 0 with training iterations, validating its effectiveness. The study shows that the improved YOLOv7-U-Net combined network provides a more effective solution for crop pest and disease detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Technology and Security Systems · Remote Sensing and Land Use
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Civil and Transportation Engineering, Hebei University of Technology, Tianjin 300401, China
School of Mechanical Engineering, Hebei University of Technology, Tianjin 300401, China
School of Chemical Engineering, Hebei University of Technology, Tianjin 300401, China
Funding
National Natural Science Foundation of China
References (22)
Show source-provided references
1. Quantitative Estimation of Wheat Stripe Rust Disease Index Using Unmanned Aerial Vehicle Hyperspectral Imagery and Innovative Vegetation Indices10.1109/TGRS.2023.3292130 ↗
2. Integrated pest management (IPM) in agriculture and its role in maintaining ecological balance and biodiversity
3. Sharing decision-making tools for pest management may foster implementation of Integrated Pest Management10.1007/s12571-023-01402-3 ↗
4. Ahmed, M.Z., Hasan, A., Rubaai, K., Hasan, K., Pu, C., and Reed, J.H. (2023, January 21–23). Deep Learning Assisted Channel Estimation for Cell-Free Distributed MIMO Networks. Proceedings of the 19th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Montreal, QC, Canada.10.1109/WiMob58348.2023.10187876 ↗
5. Applying convolutional neural networks for detecting wheat stripe rust transmission centers under complex field conditions using RGB-based high spatial resolution images from UAVs10.1016/j.compag.2022.107211 ↗
6. Transformer-based Multi-scale Feature Aggregation for Crop Disease Detection
7. Research on knowledge graph-based question and answer system for crop pests and diseases
8. Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., and Dong, L. (2022, January 18–24). Swin Transformer V2: Scaling Up Capacity and Resolution. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01170 ↗
9. Geudtner, D., Tossaint, M., Davidson, M., and Torres, R. (2021, January 11–16). Copernicus Sentinel-1 Next Generation Mission. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Brussels, Belgium.10.1109/IGARSS47720.2021.9554226 ↗
10. Causality-inspired crop pest recognition based on Decoupled Feature Learning10.1002/ps.8314 ↗
11. Research on the classification of typical crops in remote sensing images by improved U-Net algorithm
12. Comparison of different computer vision methods for vineyard canopy detection using UAV multispectral images10.1016/j.compag.2024.109277 ↗
13. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2023, January 17–24). YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
14. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
15. Roy, A.G., Navab, N., and Wachinger, C. (2018, January 16–20). Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Granada, Spain.10.1007/978-3-030-00928-1_48 ↗
16. Si, C., Huang, Z., Jiang, Y., and Liu, Z. (2024, January 16–22). FreeU: Free Lunch in Diffusion U-Net. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.00453 ↗
17. Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018). CBAM: Convolutional Block Attention Module. Computer Vision–ECCV 2018, Springer.10.1007/978-3-030-01252-6 ↗
18. Adaptive Attention Mechanisms in U-Net for Hyperspectral Crop Classification
19. Jia, J., Lei, R., Qin, L., and Wei, X. (2024). i5mC-DCGA: An improved hybrid network framework based on the CBAM attention mechanism for identifying promoter 5mC sites. BMC Genom., 25.10.1186/s12864-024-10154-z ↗
20. Synthetic Data Generation for Small Lesion Detection in Precision Agriculture
21. Wang, E.F. (2024, January 16–22). YOLOv8: Scalable Real-Time Object Detection with Dynamic Anchor Optimization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.
22. Cross-domain Generalization for Crop Pest Recognition under Variable Lighting