结合深度学习、优化算法与物联网传感器的植物病害检测综述
关键词:
深度学习; 检测; 叶片病害; 元启发式优化方法; 植物病害识别摘要
作物病害是农业部门面临的主要问题之一。采用自动化技术检测植物病害具有明显优势：它能够及早发现问题，并大幅减少大型农场的巡查工作量。众多研究者提出了多种元启发式优化方法与深度学习新技术来识别和分类植物病害。本文分析了大量基于物联网（IoT）的植物病害自动识别与检测方法。用于检测植物病害的自动模块把数据提供给系统所维护的汇聚节点，从而支持基于物联网的监测。目前已存在众多基于植物病害与计算机视觉的方法，本文共考察33篇论文。本研究还就如何提升物联网集成的植物病害检测与识别能力给出了全面的认识，并指出了各类问题与研究空白以及可能的研究方向。Abstract
Crop diseases are one of the main problems facing the farming sector. Detecting plant diseases using some automatic techniques is advantageous because it recognizes problems early and eliminates a significant amount of monitoring effort on massive farms. Numerous investigators have created various metaheuristic optimizing and an innovative technique for deep learning to recognize and classify plant illnesses. This research analyzes many IoT-based methods for automated plant disease identification and detection. The automatic module for detecting plant diseases provides data to a sink node that the system maintains to facilitate IoT-based monitoring. Numerous methods based on plant disease and computer vision exist. Thirty-three papers in all are examined here. This research also offers a thorough understanding of how to enhance IoT-integrated plant disease detection and identification capabilities. In addition to this, various problems and research gaps are noted along with potential research.References
[1] 杨翰琨, 朱博威, 张彦敏, 等. 基于深度学习的植物病害图像识别算法综述. 电子技术应用, 2025, 51(1): 1-7.
[2] Pham T N, Van Tran L, Dao S V T. Early disease classification of mango leaves using feed-forward neural network and hybrid metaheuristic feature selection. IEEE Access, 2020, 8: 189960-189973.
[3] 沈川, 李夏. 深度学习在作物病害识别方面的研究进展. 河南农业科学, 2026(3): 19-27.
[4] Lee S H, Goëau H, Bonnet P, et al. New perspectives on plant disease characterization based on deep learning. Computers and Electronics in Agriculture, 2020, 170: 105220.
[5] Too E C, Yujian L, Njuki S, et al. A comparative study of fine-tuning deep learning models for plant disease identification. Computers and Electronics in Agriculture, 2019, 161: 272-279.
[6] 王涛, 黄语燕, 陈永快, 等. 高光谱成像技术在叶菜无损检测中的应用研究进展. 现代农业科技, 2024(13): 168-172.
[7] Thomas S, et al. Benefits of hyperspectral imaging for plant disease detection and plant protection: a technical perspective. Journal of Plant Diseases and Protection, 2018, 125(1): 5-20.
[8] 沈熠辉, 何惠彬, 陈小宇, 等. 融合SKNet与MobilenetV3的芒果叶片病虫害分类方法. 福建农业学报，2024, 39(5): 584-592.