ABSTRACT
This study focuses on the development needs of smart ecological agriculture and proposes an improved network model based on ResNet50. The research aims to improve the accuracy and efficiency of automatic identification of corn pests and diseases. Firstly, the collected leaf data of corn pests and diseases were enhanced. The purpose of doing so is to expand the amount of data and achieve a balance between various types of data. Secondly, the size of the network convolution kernel was adjusted. And introduce SE attention mechanism to the backend of the network to optimize the effect of network detail feature extraction. Finally, through experimental verification, the results show that the network model has high accuracy and robustness in identifying corn pests and diseases, and can effectively improve the efficiency of corn pest control.
- Huang Song. 2022. Research on Mobile Corn Leaf Disease and Pest Identification Technology Based on Deep Learning. Huazhong Agricultural University, DOI: 10.27158/d.cnki.ghznu.2022.000608.Google ScholarCross Ref
- Wang Jianhua. 2021. Corn planting management and pest control measures Agricultural Technology and Information. (23): 32-34 DOI: 10.15979/j.cnki.cn62-1057/s.2021.23.012.Google ScholarCross Ref
- Liu Bo; Hu Chunmei. 2020. Research on New Cultivation Techniques and Pest Control Measures for Corn in the New Era. Seed Technology, 38 (03): 87+89.Google Scholar
- W. S. R. Souza, A. N. Alves and D. L. Borges. 2019. A Deep Learning Model for Recognition of Pest Insects in Maize Plantations. 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy, pp. 2285-2290, doi: 10.1109/SMC.2019.8914428.Google ScholarDigital Library
- Li L, Zhang S, Wang B. 2021. Plant disease detection and classification by deep learning—a review. IEEE Access, 9: 56683-56698.Google ScholarCross Ref
- Haque, M. Marwaha, S. Deb, C. K., Nigam, S., Arora, A., Hooda, K. S., 2022. Deep learning-based approach for identification of diseases of maize crop.Sci. Rep.12, 1–14. doi: 10.1038/s41598-022-10140-z.Google ScholarCross Ref
- He. K. Zhang, X. Ren. S. 2016. Deep Residual Learning for Image Recognition// Proceedings of the IEEE conference on computer vision and pattern recognition. 770-778.Google Scholar
- Zhang. X. Huang, Y. Li Q. 2018. Improved Residual Networks for Image and Video Recognition// Proceedings of the 2018 ACM on Multimedia Conference. 948-956.Google Scholar
- Simonyan, Karen, and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556Google Scholar
- Hu, Jie, 2017. Squeeze-and-Excitation Networks. arXiv preprint arXiv:1709.01507Google Scholar
- Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. CBAM: Convolutional Block Attention Module. arXiv preprint arXiv:1807.06521.Google Scholar
- Vaswani, Ashish, 2017. Attention is all you need. arXiv preprint arXiv:1706.03762.Google Scholar
- Hu Mengjiao. 2023. Research on corn leaf disease and pest identification system based on improved YOLOv5s. Hebei Normal University of Science and Technology, DOI: 10.27741/dcnki.ghbkj. 000174.Google ScholarCross Ref
- Zhang Li; Lin Xiangrui; Zhang Yu; Guo Chunyang. 2022. Research on corn pest and disease classification based on deep learning [J] Intelligent IoT Technology, 5 (02): 28-31.Google Scholar
- Ding Chenghui. 2020. Development and Implementation of an Intelligent Identification System for Maize Leaf Diseases and Pests [D] Northeast Agricultural University, DOI: 10.27010/d.cnki.gdbnu. 001020.Google ScholarCross Ref
Recommendations
Detection of citrus pests in double backbone network based on single shot multibox detector
Highlights- Double-trunk network is proposed to detect pests on citrus leaves.
- The proposed ...
AbstractTo prevent and control agricultural diseases and insect pests, the timely detection and accurate identification of crop diseases and insect pests are significant. Studies have shown that pests on plant surfaces are challenging to ...
Research on Recognition Model of Crop Diseases and Insect Pests Based on Convolutional Neural Network
AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern RecognitionMost of the traditional detection methods for crop diseases and insect pests are manually operated in the field according to the experience and technology of the staff, which have the disadvantages of long time and low efficiency. With the development of ...
Identification Method for Rice Pests with Small Sample Size Problems Combining Deep Learning and Metric Learning
Pattern Recognition and Computer VisionAbstractTo achieve accurate identification of rice pests with small sample size problems under complex backgrounds, we proposed a rice pest identification method combining deep learning and metric learning. To overcome the effect of the complex background ...
Comments