基于计算机视觉的作物病害监测服务平台设计与研究  

Design and Research of Crop Disease Monitoring Service Platform Based on Computer Vision

作　　者：林开颜[1] 梅飞 吴军辉[1] 郭文刚 陈杰[1] 司慧萍[1] LIN Kaiyan;MEI Fei;WU Junhui;GUO Wengang;CHEN Jie;SI Huiping(Modern Agricultural Science and Engineering Institute,Tongji University,Shanghai 200092,China)

机构地区：[1]同济大学现代农业科学与工程研究院,上海200092

出　　处：《中国农业科技导报》2023年第6期89-96,共8页Journal of Agricultural Science and Technology

基　　金：国家重点研发计划项目(2020YFD1100603)。

摘　　要：病害是威胁作物生长的主要因素,其特征复杂、变化多样。农业从业人员如缺乏专业知识,往往难以准确识别。以往图像识别方法常针对单一作物,图像分割后提取病害特征进行识别,无法适应多种作物。针对此问题,以水稻、番茄、柑橘、苹果为研究对象,以ResNet模型为基础构建深度学习网络框架,设计了含Squeeze-and-Excitation(SE)模块全新的全连接层,导入在ImageNet上预训练的权重,并在病害数据集上训练得到病害模型。为扩充图像数据,对训练集原图进行了亮度增减、随机旋转与镜面翻转等操作。基于扩充后的训练集进行病害识别和病害程度的分级研究。结果表明,对水稻、番茄、柑橘、苹果平均病害程度识别的准确率为94.16%,平均病害种类识别的准确率为92.45%;并利用训练好的模型基于c#.net core开发了病害监测平台,可实现作物病害的智能识别。Diseases are the main factors threatening crop yield,and their characteristics are complex and varied.It is often difficult to accurately identify them for agricultural practitioners lack professional knowledge.In the past,image recognition methods aimed at a single crop,and extracted disease features for recognition after image segmentation,which could not adapt to multiple crops.Aiming at this problem,rice,tomato,citrus and apple were as the research objects,a deep learning network framework was built based on ResNet model,and a new full connection layer containing Squeeze-and-Extension(SE)module was designed.The weight of pre-training on ImageNet was imported,and the disease model was trained on the disease data set.In order to expand the image data,the original image of the training set was increased or decreased in brightness,randomly rotated and mirror flipped.Based on the expanded training set,the disease identification and disease degree grading were studied.The results showed that the average disease degree accuracy rate of identifying rice,citrus,tomato and apple was 94.16%,and the average disease type accuracy rate was 92.45%.The disease monitoring platform was developed based on the trained model and c#.net core to realize the intelligent identification of crop diseases.

关 键 词：深度学习 病害识别 ResNet 迁移学习 

分 类 号：S126[农业科学—农业基础科学] S43