基于改进的U-Net网络模型的叶片病害检测
Leaf disease detection based on improved U-Net network model
刘林 1林山驰 1李相国 1冯敏 1许亮2
作者信息
- 1. 广东宏景科技股份有限公司,广东 广州 510145;智慧城市云边端协同技术广东省工程研究中心,广东 广州 510660
- 2. 中国科学院 长春光学精密机械与物理研究所,吉林 长春 130033;吉林省农业高光谱应用信息数据库,吉林 长春 130033
- 折叠
摘要
为了满足作物病虫害绿色防治对病虫害程度检测的需求,设计了一种改进的U-Net网络模型用于作物叶片病虫害程度的检测.首先,选择ResNet50网络作为模型的主干网络,借助迁移学习来提升训练收敛速度和降低计算成本.其次,引入注意力机制对U-Net网络的各层特征提取和融合进行优化,以提高网络模型接收关键信息的能力.实验结果表明,改进的U-Net512网络模型具有最优的检测性能,平均检测精度达到90.14%,平均绝对误差为276.3.通过分析模型不同采样深度下的各层特征图发现,注意力机制的引入使网络模型能够获取并融合叶片整体特征和病害区域特征两个维度的信息,进一步提升模型检测性能.这种方法不仅能够有效地检测作物叶片的病虫害程度,而且具有较高的准确性和可靠性,有助于实现作物病虫害的绿色防治.
Abstract
To meet the demand of green prevention and control of crop diseases and pests for the detection of disease and pest severity,an improved U-Net network model is designed for the detection of crop leaf disease and pest severity.First,the ResNet50 network is selected as the backbone network of the model,and transfer learning is used to improve the training convergence speed and reduce the computational cost.Second,the attention mechanism is introduced to optimize the feature extraction and fusion of each layer of the U-Net network,so as to improve the ability of the network model to receive key information.The experimental results show that the improved U-Net512 network model has the best detection performance,with an average detection accuracy of 90.14%and an average absolute error of 276.3.By analyzing the feature maps of each layer of the model under different sampling depths,it is found that the introduction of attention mechanism enables the network model to obtain and fuse two dimensions of information:the overall feature of the leaf and the disease area feature,which further improves the model detection performance.This method can not only effectively detect the disease and pest severity of crop leaves,but also has high accuracy and reliability,which is conducive to achieving green prevention and control of crop diseases and pests.
关键词
病虫害检测/改进U-Net网络/注意力机制/病虫害防治Key words
pest detection/U-Net network/attention gate/pest control引用本文复制引用
基金项目
广东省重点研发计划(2019B020214001)
出版年
2024
国家科技期刊平台
NSTL
万方数据