基于改进BiSeNet的葡萄黑麻疹病害程度分级预测  

Prediction of severity grading of black measles disease in grapes based on improved BiSeNet

作　　者：白春晖 陈健 郜鲁涛[1] BAI Chun-hui;CHEN Jian;GAO Lu-tao(College of Big Data/Yunnan Engineering Technology Research Center of Agricultural Big Data/Yunnan Engineering Research Center for Big Data Intelligent Information Processing of Green Agricultural Products,Yunnan Agricultural University,Kunming 650201,China)

机构地区：[1]云南农业大学大数据学院/云南省农业大数据工程技术研究中心/云南省绿色农产品大数据智能信息处理工程研究中心,昆明650201

出　　处：《湖北农业科学》2024年第5期187-193,222,共8页Hubei Agricultural Sciences

基　　金：云南省基础研究专项面上项目(202101AT070248)。

摘　　要：为了准确对葡萄(Vitis vinifera L.)黑麻疹病害程度进行分级预测,通过语义分割模型将叶片部分和病斑部分分割出来,以同一叶片上病斑面积与总叶面积的比值作为疾病严重程度分级的依据,对葡萄黑麻疹病害程度进行分级预测。精确标注了PlantVillage公开数据库中的419张葡萄疾病图像,细分为背景、叶片和病斑3个类别,并应用了数据增强技术增加样本多样性。以BiSeNet作为基准模型,引入GhostNet作为上下文路径的主干提取网络,不仅保持了较小的模型参数量,而且在精度上实现了明显提升,满足病害程度分级预测的需求。提出了累加空洞空间金字塔池化(CASPP)模块,用来替换BiSeNet模型中单一的上下文嵌入模块,以增强BiSeNet模型的多尺度上下文信息提取能力,提高了模型的分割精度。经过测试,本研究模型在测试集中的平均交并比为94.11%,在对葡萄黑麻疹病害程度进行分级预测时,准确率达98.21%,能够精确地对葡萄黑麻疹病害程度进行分级预测。In order to accurately grade and predict the degree of black measles disease in grapes(Vitis vinifera L.),a semantic segmen-tation model was used to separate the leaf and lesion parts.The ratio of lesion area to total leaf area on the same leaf was used as the ba-sis for disease severity grading,and the degree of black measles disease in grapes was predicted.419 grapes disease images from the PlantVillage public database were accurately annotated and subdivided into three categories:background,leaves,and lesions,and data augmentation techniques were applied to increase sample diversity.Using BiSeNet as the benchmark model and introducing Ghost-Net as the backbone extraction network for context paths not only maintained a small number of model parameters,but also achieved a significant improvement in accuracy,meeting the needs of disease severity classification prediction.A cumulative atrous spatial pyra-mid pooling(CASPP)module was proposed to replace the single context embedding module in the BiSeNet model,in order to enhance the multi-scale context information extraction ability of the BiSeNet model and improve the segmentation accuracy of the model.After testing,the average Intersection over to Union of this research model in the test set was 94.11%.When predicting the degree of black measles disease in grapes,the accuracy reached 98.21%,which could accurately predict the degree of black measles disease in grapes.

关 键 词：BiSeNet 深度学习 语义分割 病害程度 分级预测 葡萄(Vitis vinifera L.) 黑麻疹 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]