基于深度学习的植物病害图像识别算法综述  

Review of plant disease image recognition algorithms based on deep learning

作　　者：杨翰琨 朱博威 张彦敏[2] 徐以东 Yang Hankun;Zhu Bowei;Zhang Yanmin;Xu Yidong(Yantai Research Institute,Harbin Engineering University,Yantai 265500,China;Hubei Key Laboratory of MarineElectromagnetic Detection and Control,Wuhan Second Ship Design and Research Institute,Wuhan 430064,China)

机构地区：[1]哈尔滨工程大学烟台研究生院,山东烟台265500 [2]武汉第二船舶设计研究所海洋电磁探测与控制湖北省重点实验室,武汉湖北430064

出　　处：《电子技术应用》2025年第1期1-7,共7页Application of Electronic Technique

基　　金：国家自然科学基金项目(52101383)。

摘　　要：植物病害对农业生产和粮食安全构成严重威胁,及时准确地识别和处理成为关键步骤。综述了深度学习在植物病害识别中的应用现状、挑战及未来发展方向。首先介绍了植物病害的重要性和传统识别方法的局限性,然后探讨了深度学习技术的优势及其在植物病害识别中的应用前景,特别是YOLO系列模型在植物病害实时检测中的应用。同时对比了常见的深度学习算法在植物病害识别中的性能,以及对数据集多样性、实时性和灾难性遗忘等挑战进行了分析。最后,提出了持续学习和模型更新的重要性,并展望了未来研究方向。Plant diseases pose a significant threat to agricultural production and food security,making timely and accurate identi‐fication and treatment critical.This article reviews the current status,challenges,and future directions of deep learning in plant disease identification.It begins by outlining the importance of plant diseases and the limitations of traditional identification meth‐ods,then explores the advantages of deep learning technologies and their application prospects in plant disease identification,es‐pecially the use of YOLO series models for real-time detection.Additionally,this article compares the performance of common deep learning algorithms in plant disease identification,and analyzes challenges such as dataset diversity,real-time performance,and catastrophic forgetting.Finally,it emphasizes the importance of continuous learning and model updates,and presents future research directions.

关 键 词：灾难性遗忘 持续学习 深度学习 植物病害识别 YOLO 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]