CROP PEST AND DISEASE IDENTIFICATION SYSTEM BASED ON MUTUAL LEARNING
Keywords:
Crop disease, Deep learning, Mutual learningAbstract
As the fundamental industry supporting the national economy, agricultural production is seriously restricted by frequent occurrences of crop pests and diseases, which have been proven to cause enormous economic losses worldwide every year. Therefore, the rapid and accurate identification of crop pests and diseases is widely regarded as a crucial prerequisite for the sustainable development of green agriculture and high-quality agricultural production. Traditional pattern classification algorithms and representative deep learning models including VGG and ResNet have been gradually applied in the field of pest and disease identification, yet most deep networks are confronted with great challenges in real-world deployment on mobile and edge devices due to their excessively large number of parameters and high computational complexity. To effectively tackle this application bottleneck, a lightweight BMV3 network based on the mutual learning framework is proposed in this paper. After heterogeneous knowledge interaction and mutual learning with ResNet50, the identification accuracy of the proposed model is significantly improved by 2.6%, and the dual optimization of high identification accuracy and flexible terminal deployment is successfully realized.References
[1] Zhang Yiyang, Liu Jie, Bian Yue, et al. Analysis of the Occurrence Trends and Causes of Major Crop Diseases and Pests in China in 2026. China Plant Protection Guide, 2026, 46(01): 45-49.
[2] Khan A I, Quadri S M K, Banday S, et al. Deep diagnosis: A real-time apple leaf disease detection system based on deep learning. Computers and Electronics in Agriculture, 2022, 198: 107093
[3] Fang Yingying, Pan Yanhong, Pan Xinling, et al. Design of a Crop Disease and Pest Identification System Based on Deep Learning. Smart Agriculture Guide, 2026, 6(03): 23-28. DOI: 10.20028/j.zhnydk.2026.03.006.
[4] Gao R, Wang R, Feng L, et al. Dual-branch, efficient, channel attention-based crop disease identification. Computers and Electronics in Agriculture, 2021, 190: 106410.
[5] Xu Yuchao, Wu Qian, Zhang Bingyuan, et al. Advances in the application of lightweight deep learning networks in crop target detection. Chinese Journal of Agricultural Mechanization, 2025, 46(03): 261-270. DOI: 10.13733/j.jcam.issn.2095-5553.2025.03.038.
[6] Karar M E, Alsunaydi F, Albusaymi S, et al. A new mobile application of agricultural pests recognition using deep learning in cloud computing system. Alexandria Engineering Journal, 2021, 60(5): 4423-4432.
[7] Boogaard F P, Rongen K S A H, Kootstra G W. Robust node detection and tracking in fruit-vegetable crops using deep learning and multi-view imaging. Biosystems Engineering, 2020, 192: 117-132.
[8] Zhang Y, Tao X, Hospedales T M, et al. Deep mutual learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4320-4328.
[9] Yang Xiang, Duan Junming, Dong Minggang. Image recognition method for plant diseases for mobile devices and its application. Jiangsu Agricultural Sciences, 2023, 51(04): 191-197. DOI: 10.15889/j.issn.1002-1302.2023.04.028.
[10] Liu Bin, Jia Runchang, Zhu Xianyu, et al. A lightweight identification model for apple leaf diseases and pests for mobile devices. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(06): 130-139.