Sematic segmentation of loess landslides with STAPLE mask and fully connected conditional random field

被引:0
|
作者
Huajin Li
Yusen He
Qiang Xu
Jiahao Deng
Weile Li
Yong Wei
Jingren Zhou
机构
[1] Chengdu University,School of Architecture and Civil Engineering
[2] Chengdu University of Technology,State Key Laboratory of Geo
[3] Grinnell College,hazard Prevention and Geo
[4] DePaul University,Environment Protection
[5] Architectural Engineering College,Data Analysis and Social Inquiry Lab (DASIL)
[6] Guizhou Minzu University,College of Computing and Digital Media
[7] Sichuan University,State Key Laboratory of Hydraulics and Mountain River Engineering
来源
Landslides | 2023年 / 20卷
关键词
Loess landslide; Landslide segmentation; Geohazard assessment; Landslide measurement; Deep learning;
D O I
暂无
中图分类号
学科分类号
摘要
Loess landslides are widely distributed in Northern China and pose a significant threat to human life, natural resources, and infrastructure in mountainous regions. Accurate segmentation and measurement of loess landslides is crucial to documenting their occurrence and extent and investigating the distribution, types, and patterns of slope failures. The measurement of landslides also assists in assessing their susceptibility and risk. Herein, a novel loess landslide segmentation and measurement framework based on deep learning is proposed. Multiple experts label the ground-truth landslide regions, and simultaneous truth and performance level estimation (STAPLE) masks are generated. The U-Net segmentation algorithm is trained using a supervised approach to segment the loess landslide region. The fully connected conditional random field is integrated into the U-Net to further optimize the segmentation quality. In the final step, the predicted landslide boundaries are visualized, and the diameters (e.g., length and width) of the segmentation outcome are computed simultaneously. Four state-of-the-art segmentation algorithms are selected for the comparative analysis. The computational results demonstrate that the proposed framework outperforms all the other algorithms tested in terms of segmentation accuracy and boundary errors. The results verify the advantages of using STAPLE and U-Net integrated with a conditional random field.
引用
收藏
页码:367 / 380
页数:13
相关论文
共 50 条
  • [1] Sematic segmentation of loess landslides with STAPLE mask and fully connected conditional random field
    Li, Huajin
    He, Yusen
    Xu, Qiang
    Deng, Jiahao
    Li, Weile
    Wei, Yong
    Zhou, Jingren
    [J]. LANDSLIDES, 2023, 20 (02) : 367 - 380
  • [2] Fine Segmentation of Tiny Blood Vessel Based on Fully-Connected Conditional Random Field
    Wang, Chenglong
    Oda, Masahiro
    Yoshino, Yasushi
    Yamamoto, Tokunori
    Mori, Kensaku
    [J]. MEDICAL IMAGING 2018: IMAGE PROCESSING, 2018, 10574
  • [3] 3D Point Cloud Segmentation Using a Fully Connected Conditional Random Field
    Lin, Xiao
    Casas, Josep R.
    Pardas, Montse
    [J]. 2017 25TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2017, : 66 - 70
  • [4] A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images
    Ignacio Orlando, Jose
    Prokofyeva, Elena
    Blaschko, Matthew B.
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2017, 64 (01) : 16 - 27
  • [5] Semantic segmentation of mechanical assembly using selective kernel convolution UNet with fully connected conditional random field
    Chen, Chengjun
    Zhang, Chunlin
    Wang, Jinlei
    Li, Dongnian
    Li, Yang
    Hong, Jun
    [J]. MEASUREMENT, 2023, 209
  • [6] EFFICIENT SEMANTIC SEGMENTATION OF MAN-MADE SCENES USING FULLY-CONNECTED CONDITIONAL RANDOM FIELD
    Li, Weihao
    Yang, Michael Ying
    [J]. XXIII ISPRS CONGRESS, COMMISSION III, 2016, 41 (B3): : 633 - 640
  • [7] A Stochastically Fully Connected Conditional Random Field Framework for Super Resolution OCT
    Boroomand, A.
    Tan, B.
    Wong, A.
    Bizheva, K.
    [J]. OPTICAL COHERENCE TOMOGRAPHY AND COHERENCE DOMAIN OPTICAL METHODS IN BIOMEDICINE XXI, 2017, 10053
  • [8] Fully convolutional networks semantic segmentation based on conditional random field optimization
    Wu, Qian
    Gu, Jinan
    Wu, Chen
    Li, Jin
    [J]. JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING, 2021, 21 (05) : 1405 - 1415
  • [9] RETINAL VESSEL SEGMENTATION VIA DEEP LEARNING NETWORK AND FULLY-CONNECTED CONDITIONAL RANDOM FIELDS
    Fu, Huazhu
    Xu, Yanwu
    Wong, Damon Wing Kee
    Liu, Jiang
    [J]. 2016 IEEE 13TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2016, : 698 - 701
  • [10] Semantic Segmentation of Polarimetric SAR Image Based on Dual-Channel Multi-Size Fully Connected Convolutional Conditional Random Field
    Kong, Yingying
    Li, Qiupeng
    [J]. REMOTE SENSING, 2022, 14 (06)