AC-UNet: an improved UNet-based method for stem and leaf segmentation in Betula luminifera

被引:5
|
作者
Yi, Xiaomei [1 ]
Wang, Jiaoping [1 ]
Wu, Peng [1 ]
Wang, Guoying [1 ]
Mo, Lufeng [1 ]
Lou, Xiongwei [1 ]
Liang, Hao [1 ]
Huang, Huahong [1 ]
Lin, Erpei [1 ]
Maponde, Brian Tapiwanashe [1 ]
Lv, Chaihui [2 ]
机构
[1] Zhejiang A&F Univ, Coll Math & Comp Sci, Hangzhou, Peoples R China
[2] Hangzhou Ganzhi Technol Co Ltd, Hangzhou, Peoples R China
来源
关键词
Betula luminifera; stem and leaf division; UNET; hollow space pyramidal pooling; crossed attention;
D O I
10.3389/fpls.2023.1268098
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Plant phenotypic traits play an important role in understanding plant growth dynamics and complex genetic traits. In phenotyping, the segmentation of plant organs, such as leaves and stems, helps in automatically monitoring growth and improving screening efficiency for large-scale genetic breeding. In this paper, we propose an AC-UNet stem and leaf segmentation algorithm based on an improved UNet. This algorithm aims to address the issues of feature edge information loss and sample breakage in the segmentation of plant organs, specifically in Betula luminifera. The method replaces the backbone feature extraction network of UNet with VGG16 to reduce the redundancy of network information. It adds a multi-scale mechanism in the splicing part, an optimized hollow space pyramid pooling module, and a cross-attention mechanism in the expanding network part at the output end to obtain deeper feature information. Additionally, Dice_Boundary is introduced as a loss function in the back-end of the algorithm to circumvent the sample distribution imbalance problem. The PSPNet model achieves mIoU of 58.76%, mPA of 73.24%, and Precision of 66.90%, the DeepLabV3 model achieves mIoU of 82.13%, mPA of 91.47%, and Precision of 87.73%, on the data set. The traditional UNet model achieves mIoU of 84.45%, mPA of 91.11%, and Precision of 90.63%, and the Swin-UNet model achieves . The mIoU is 79.02%, mPA is 85.99%, and Precision is 88.73%. The AC-UNet proposed in this article achieved excellent performance on the Swin-UNet dataset, with mIoU, mPA, and Precision of 87.50%, 92.71%, and 93.69% respectively, which are better than the selected PSPNet, DeepLabV3, traditional UNet, and Swin-UNet. Commonly used semantic segmentation algorithms. Experiments show that the algorithm in this paper can not only achieve efficient segmentation of the stem and leaves of Betula luminifera but also outperforms the existing state-of-the-art algorithms in terms of both speed. This can provide more accurate auxiliary support for the subsequent acquisition of plant phenotypic traits.
引用
收藏
页数:16
相关论文
共 50 条
  • [31] Segmentation of Pulmonary Nodules Based on Improved UNet plus
    Dong, Li
    Liu, Hongying
    2021 14TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2021), 2021,
  • [32] Research on Lung Tumor Cell Segmentation Method Based on Improved UNet Algorithm
    Sun, Jun
    Chen, Weimin
    Zhang, Longzhen
    Yan, Xundong
    SCIENTIFIC PROGRAMMING, 2022, 2022
  • [33] A Spinal MRI Image Segmentation Method Based on Improved Swin-UNet
    Cao, Jie
    Fan, Jiacheng
    Chen, Chin-Ling
    Wu, Zhenyu
    Jiang, Qingxuan
    Li, Shikai
    NETWORK-COMPUTATION IN NEURAL SYSTEMS, 2024,
  • [34] DEVELOPMENT AND ASSESSMENT OF UNET-BASED AUTOMATIC SEGMENTATION METHOD TO MEASURE KNEE CARTILAGE THICKNESS USING MAGNETIC IMAGING
    Margain, Paul
    Mourad, Charbel
    Shokouhyan, Seyed Mohammadreza
    Jolles, Brigitte M.
    Omoumi, Patrick
    Favre, Julien
    OSTEOARTHRITIS AND CARTILAGE, 2024, 32 : S370 - S371
  • [35] A Medical Image Segmentation Method Based on Improved UNet 3+ Network
    Xu, Yang
    Hou, Shike
    Wang, Xiangyu
    Li, Duo
    Lu, Lu
    DIAGNOSTICS, 2023, 13 (03)
  • [36] Brain Tumor MRI Segmentation Method Based on Improved Res-UNet
    Li, Xue
    Fang, Zhenqi
    Zhao, Ruhua
    Mo, Hong
    IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION, 2024, 8 : 652 - 657
  • [37] GA-UNet: UNet-based framework for segmentation of 2D and 3D medical images applicable on heterogeneous datasets
    Amrita Kaur
    Lakhwinder Kaur
    Ashima Singh
    Neural Computing and Applications, 2021, 33 : 14991 - 15025
  • [38] GA-UNet: UNet-based framework for segmentation of 2D and 3D medical images applicable on heterogeneous datasets
    Kaur, Amrita
    Kaur, Lakhwinder
    Singh, Ashima
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (21): : 14991 - 15025
  • [39] Automated detection of textured-surface defects using UNet-based semantic segmentation network
    Enshaei, Nastaran
    Ahmad, Safwan
    Naderkhani, Farnoosh
    2020 IEEE INTERNATIONAL CONFERENCE ON PROGNOSTICS AND HEALTH MANAGEMENT (ICPHM), 2020,
  • [40] HIGH-PRECISION SEGMENTATION METHOD OF DISTRIBUTED PHOTOVOLTAIC BUILDINGS BASED ON IMPROVED UNET
    Xu X.
    Zhang H.
    Bai J.
    Pei R.
    Hu J.
    Tan Z.
    Taiyangneng Xuebao/Acta Energiae Solaris Sinica, 2023, 44 (11): : 82 - 90