Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 56, Issue 15, 152801(2019)

Remote Sensing Image Classification Based on DeepLab-v3+

Li Yuan1, Jishou Yuan1、*, and Dezheng Zhang2
Author Affiliations
  • 1 School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
  • 2 School of Computer and Communications Engineering, University of Science and Technology Beijing, Beijing 100083, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (14)
    Equations (0)
    References (24)
    Cited By (4)
    Tools
    Paper Information
    Topics
    Figures & Tables(14)
    System diagram of remote sensing image classification based on DeepLab-v3+

    Fig. 1. System diagram of remote sensing image classification based on DeepLab-v3+

    Download full size
    Diagrams of abtrous convolution[11]. (a) Sparse feature extraction; (b) dense feature extraction

    Fig. 2. Diagrams of abtrous convolution[11]. (a) Sparse feature extraction; (b) dense feature extraction

    Download full size
    Structure of atrous spatial pyramid pooling

    Fig. 3. Structure of atrous spatial pyramid pooling

    Download full size
    Structure of encoder-decoder module

    Fig. 4. Structure of encoder-decoder module

    Download full size
    Example of dataset. (a) Original images; (b) labels

    Fig. 5. Example of dataset. (a) Original images; (b) labels

    Download full size
    Loss curve

    Fig. 6. Loss curve

    Download full size
    64 feature maps obtained from the first convolution layer

    Fig. 7. 64 feature maps obtained from the first convolution layer

    Download full size
    Segmentation effect by DeepLab-v3+; (a) Original image; (b) segmentation result by DeepLab-v3+

    Fig. 8. Segmentation effect by DeepLab-v3+; (a) Original image; (b) segmentation result by DeepLab-v3+

    Download full size
    Comparison of loss of different models

    Fig. 9. Comparison of loss of different models

    Download full size
    Comparison of segmentation results of DeepLab-v3+ and other models. (a) Original images; (b) segmentation results of FCN; (c) segmentation results of U-Net; (d) segmentation results of DeepLab-v3+

    Fig. 10. Comparison of segmentation results of DeepLab-v3+ and other models. (a) Original images; (b) segmentation results of FCN; (c) segmentation results of U-Net; (d) segmentation results of DeepLab-v3+

    Download full size
    Segmentation results of DeepLab-v3+ and other models on GID dataset. (a) Original image; (b) segmentation result of FCN; (c) segmentation result of U-Net; (d) segmentation result of DeepLab-v3+

    Fig. 11. Segmentation results of DeepLab-v3+ and other models on GID dataset. (a) Original image; (b) segmentation result of FCN; (c) segmentation result of U-Net; (d) segmentation result of DeepLab-v3+

    Download full size

    • Table 1. Training parameters

      View table

      Table 1. Training parameters

      ParameterValue
      base_lr0.0001
      lr_decay5
      batch_size10
      weight_decay0.0001
      max_iter100

    • Table 2. Precision and running time of DeepLab-v3+ and other models

      View table

      Table 2. Precision and running time of DeepLab-v3+ and other models

      ModelMIoUTime /h
      FCN0.50681.9
      U-Net0.50743.1
      DeepLab-v3+0.57431.2

    • Table 3. Precision of DeepLab-v3+ and other models on GID dataset

      View table

      Table 3. Precision of DeepLab-v3+ and other models on GID dataset

      ModelMIoU
      FCN0.5606
      U-Net0.5782
      DeepLab-v3+0.6426
    Tools

    Get Citation

    Copy Citation Text

    Li Yuan, Jishou Yuan, Dezheng Zhang. Remote Sensing Image Classification Based on DeepLab-v3+[J]. Laser & Optoelectronics Progress, 2019, 56(15): 152801

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Remote Sensing and Sensors

    Received: Dec. 1, 2018

    Accepted: Mar. 6, 2019

    Published Online: Aug. 5, 2019

    The Author Email: Jishou Yuan (jishou_yuan@163.com)

    DOI:10.3788/LOP56.152801

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology