中国烟草科学2025，Vol.46Issue(2)：93-100,8.DOI:10.13496/j.issn.1007-5119.2025.02.012
基于迁移学习的MobileViT-CBAM鲜烟叶成熟度识别模型研究
MobileViT-CBAM Model for Fresh Tobacco Leaf Maturity Recognition Based on Transfer Learning
摘要
Abstract
To establish more economical and efficient non-destructive intelligent recognition technology for tobacco leaf maturity,a lightweight network model MobileViT-CBAM on mobile devices was constructed.Firstly,a dataset was built by collecting images of the middle and upper leaves of'Yunyan87'with different maturity.The CBAM attention mechanism module was introduced into the MobileViT structure to enhance the feature expression ability of fresh tobacco leaf maturity images.Secondly,the original activation function Swish was replaced with the smoother SMU function to help the model converge faster.Finally,transfer learning was employed to improve the training efficiency and generalization ability of the model and achieve the classification of fresh tobacco leaf maturity in complex field environment.Results showed that MobileViT-CBAM exhibited an accuracy of 92.81%in maturity classification of fresh tobacco leaves,which is significantly superior to the models of VGG16,ResNet34,Vision Transformer,Swin Transformer,MobileNetV2,and MobileViT.The proposed MobileViT-CBAM model can effectively identify the maturity degree of tobacco leaves,providing technical support for the visual system of intelligent tobacco harvesting equipment.关键词
鲜烟叶成熟度/轻量级/分类模型/注意力机制Key words
maturity of tobacco fresh leaf/lightweight/classification model/attention mechanism分类
农业科技引用本文复制引用
赵泮真,王志生,王松峰,齐飞,胡强,王爱华,李亚纯,孟令峰,尹东,段史江..基于迁移学习的MobileViT-CBAM鲜烟叶成熟度识别模型研究[J].中国烟草科学,2025,46(2):93-100,8.基金项目
中国烟草总公司江西省烟草公司科技项目(202201011) （202201011）
中国烟草总公司科技重点项目(110202102007) （110202102007）
中国农业科学院科技创新工程(ASTIP-TRIC03) （ASTIP-TRIC03）
