改进UNet-VAE网络的土壤多类型孔隙三维分割方法  

Three-dimensional segmentation method of soil multi-category pores based on improved UNet-VAE network

作　　者：韩巧玲[1,3,4,5] 宋美慧 席本野 赵玥[1,3,4,5] 赵燕东[1,3,5] HAN Qiaoling;SONG Meihui;XI Benye;ZHAO Yue;ZHAO Yandong(School of Technology,Beijing Forestry University,Beijing 100083,China;School of Forestry,Beijing Forestry University,Beijing 100083,China;Beijing Laboratory of Urban and Rural Ecological Environment,Beijing Municipal Education Commission,Beijing 100083,China;Key Lab of State Forestry Administration for Forestry Equipment and Automation,Beijing 100083,China;Research Center for Intelligent Forestry,Beijing Forestry University,Beijing 100083,China)

机构地区：[1]北京林业大学工学院,北京100083 [2]北京林业大学林学院,北京100083 [3]北京市教育委员会城乡生态环境北京实验室,北京100083 [4]国家林业局林业装备与自动化国家重点实验室,北京100083 [5]北京林业大学智慧林业研究中心,北京100083

出　　处：《农业工程学报》2024年第18期81-89,共9页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金项目面上项目(32071838);国家自然科学基金项目青年项目(32101590)。

摘　　要：不同类型土壤孔隙结构会随生物活动和非生物作用发生形变,从而影响其生态功能,准确分割不同类型的孔隙结构对于研究孔隙结构与生态功能演变关系具有重要意义。针对单个类别孔隙的分割方法分割精度低、分类标准单一、鲁棒性差,无法准确分割和判别生物孔隙、裂隙等相交部分孔隙结构的问题。该研究针对不同类型孔隙尺度差距大的特点,提出了一种改进UNet-VAE网络模型,实现土壤多类型孔隙分割。改进UNet-VAE网络引入多尺度特征融合注意力模块,以实现多尺度信息融合和冗余信息筛选。结合变分自动编码器生成网络(variational autoencoder,VAE),引入噪声和辅助损失函数,以增强网络的泛化能力和鲁棒性。试验结果表明:改进UNet-VAE方法在土壤多类型孔隙(裂隙、生物孔、不规则孔隙和球状孔隙)三维分割中达到了93.83%的平均准确率,与次优VNet方法相比,平均准确率、精确率、召回率和F1值分别提升了3.32,5.06,8.97和8.63个百分点,特别是对于不规则孔隙4项指标分别提升了4.88,15.46,15.70和15.50个百分点,表明改进UNet-VAE法可准确分割多类型孔隙,也验证了深度学习技术在多类型孔隙判别的有效性,可为揭示土壤孔隙结构与演化研究提供有效工具。Soil pores can play a significant role in the crucial process related to soil ecological functions.However,it is still challenging on the relationship between pore structure and functional evolution,due to the lack of non-destructive and nonintrusive systems for the spatial structure of multiple types of pores.Among them,accurate segmentation of pore types and ranges was fundamental to the research.In this study,an improved UNet-VAE network was proposed to segment the multiple pores in soil for the first time.Taking the typical black soil as the research object,a Simplified Convolutional Network(SCN)was used to segment the three-dimensional data of soil pores.According to the segmented pore dataset,a combination of automatic segmentation and manual correction was used to obtain four types of soil pore structures as ground truth.A multiscale fusion attention module was proposed to filter out the redundant information generated by convolutional learning using a 3D UNet network.Local attention was used to learn the spatial features of small-scale pores(irregular and spherical pores).Global attention was used to extract the feature information of large-scale pores(cracks and biological pores),in order to fuse the multi-scale features for high segmentation accuracy in the different categories of pores.Meanwhile,the commonly used segmentation networks(such as 3D UNet,Segresnet,VNet,and UNetR network)were used to compare the segmentation of the multiple pores.The experimental results showed that the improved UNet-VAE network accurately determined the range and the category of pores.Specifically,the UNetR network was difficult to learn the features,due to the high requirement of a Transformer for the number of datasets in the large-scale cracks and biological pores.Convolutional networks(such as 3D UNet,Segresnet,and VNet)failed to learn the global and large-scale features,where the cracks with obvious planar features were classified as biological pores.Furthermore,the Segresnet,VNet,and UNetR network misclassified the s

关 键 词：土壤 孔隙 卷积神经网络 图像分割 3D UNet 注意力模块 

分 类 号：S152[农业科学—土壤学] TP391.41[农业科学—农业基础科学]