摘要
[目的/意义]根系是植物组成的重要部分,其生长发育至关重要。根系图像分割是根系表型分析的重要方法,受限于图像质量、复杂土壤环境、低效传统方法,根系图像分割存在一定挑战。[方法]为提高根系图像分割的准确性和鲁棒性,本研究以UNet模型为基础,提出了一种多尺度特征提取根系分割算法,并结合数据增强和迁移学习进一步提高改进UNet模型的泛化性和通用性。首先,获取棉花根系单一数据集和开源多作物混合数据集,基于单一数据集的消融试验测试多尺度特征提取模块(Conv_2+Add)的有效性,与UNet、PSPNet、SegNet、DeeplabV3Plus算法对比验证其优势。基于混合数据集验证改进算法(UNet+Conv_2+Add)在迁移学习的优势。[结果和讨论] UNet+Conv_2+Add相比其他算法(UNet、PSPNet、SegNet、DeeplabV3Plus),mIoU、mRecall和根系F_1调和平均值分别为81.62%、86.90%和78.39%。UNet+Conv_2+Add算法的迁移学习相比于普通训练在根系的交并比(Intersection over Union,IoU)值提升1.25%,根系的Recall值提升1.79%,F_1调和平均值提升0.92%,且模型的整体收敛速度快。[结论]本研究采用的多尺度特征提取策略能准确、高效地分割根系,为作物根系表型研究提供重要的研究基础。
[Objective]The root system is an important component of plant composition,and its growth and development are crucial for plants.Root image segmentation is an important method for obtaining root phenotype information and analyzing root growth patterns.Re‐search on root image segmentation still faces difficulties,because of the noise and image quality limitations,the intricate and diverse soil environment,and the ineffectiveness of conventional techniques.This paper proposed a multi-scale feature extraction root seg‐mentation algorithm that combined data augmentation and transfer learning to enhance the generalization and universality of the root image segmentation models in order to increase the speed,accuracy,and resilience of root image segmentation.[Methods]Firstly,the experimental datasets were divided into a single dataset and a mixed dataset.The single dataset acquisition was obtained from the experimental station of Hebei Agricultural University in Baoding city.Additionally,a self-made RhizoPot device was used to collect images with a resolution pixels of 10,200×14,039,resulting in a total of 600 images.In this experiment,100 sheets were randomly selected to be manually labeled using Adobe Photoshop CC2020 and segmented into resolution pixels of 768×768,and divided into training,validation,and test sets according to 7:2:1.To increase the number of experimental samples,an open source multi-crop mixed dataset was obtained in the network as a supplement,and it was reclassified into training,validation,and test‐ing sets.The model was trained using the data augmentation strategy,which involved performing data augmentation operations at a set probability of 0.3 during the image reading phase,and each method did not affect the other.When the probability was less than 0.3,changes would be made to the image.Specific data augmentation methods included changing image attributes,randomly cropping,ro‐tating,and flipping those images.The UNet structure was improved by designing eight different multi-scale image
作者
唐辉
王铭
于秋实
张佳茜
刘连涛
王楠
TANG Hui;WANG Ming;YU Qiushi;ZHANG Jiaxi;LIU Liantao;WANG Nan(College of mechanical and electrical engineering,Hebei Agricultural University,Baoding 071001,China;Hebei Education Examinations Authority,Shijiazhuang 050091,China;College of agronomy,Hebei Agricultural University,Baoding 071001,China)
出处
《智慧农业（中英文）》
CSCD
2023年第3期96-109,共14页
Smart Agriculture
基金
河北省教育厅青年拔尖人才计划项目(BJ2021058)
中央引导地方科技发展资金项目(236Z7402G)
华北作物改良与调控国家重点实验室自主课题(NCCIR2021ZZ-23)。
关键词
深度学习
根系图像分割
UNet
多尺度特征
迁移学习
deep learning
root image segmentation
UNet
multi-scale characteristics
transfer learning
