Very high resolution Airborne PolSAR Image Classification using Convolutional Neural Networks

被引:0
作者
Minh-Tan Pham [1 ]
Lefevre, Sebastien [1 ]
机构
[1] Univ Bretagne Sud, IRISA, CNRS, UMR 6074, Campus Tohannic,Rue Yves Mainguy, F-56000 Vannes, France
来源
13TH EUROPEAN CONFERENCE ON SYNTHETIC APERTURE RADAR, EUSAR 2021 | 2021年
关键词
SEGMENTATION;
D O I
暂无
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
In this work, we exploit convolutional neural networks (CNNs) for the classification of very high resolution (VHR) polarimetric SAR (PolSAR) data. Due to the significant appearance of heterogeneous textures within these data, not only polarimetric features but also structural tensors are exploited to feed CNN models. For deep networks, we use the SegNet model for semantic segmentation, which corresponds to pixelwise classification in remote sensing. Our experiments on the airborne F-SAR data show that for VHR PolSAR images, SegNet could provide high accuracy for the classification task; and introducing structural tensors together with polarimetric features as inputs could help the network to focus more on geometrical information to significantly improve the classification performance.
引用
收藏
页码:973 / 976
页数:4
相关论文
共 13 条
  • [1] Beyond RGB: Very high resolution urban remote sensing with multimodal deep networks
    Audebert, Nicolas
    Le Saux, Bertrand
    Lefevre, Sebastien
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 140 : 20 - 32
  • [2] SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
    Badrinarayanan, Vijay
    Kendall, Alex
    Cipolla, Roberto
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) : 2481 - 2495
  • [3] A NOTE ON THE GRADIENT OF A MULTIIMAGE
    DIZENZO, S
    [J]. COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1986, 33 (01): : 116 - 125
  • [4] Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features
    Du, Peijun
    Samat, Alim
    Waske, Bjoern
    Liu, Sicong
    Li, Zhenhong
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2015, 105 : 38 - 53
  • [5] Guiotte F., IEEE Geoscience and Remote Sensing Letters
  • [6] Long J, 2015, PROC CVPR IEEE, P3431, DOI 10.1109/CVPR.2015.7298965
  • [7] Ma Y., 2019, Progress In Electromagnetics Research, V83, DOI [10.2528/PIERB18112104, DOI 10.2528/PIERB18112104]
  • [8] Fusion of Polarimetric Features and Structural Gradient Tensors for VHR PolSAR Image Classification
    Minh-Tan Pham
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2018, 11 (10) : 3732 - 3742
  • [9] Pham MT, 2015, INT GEOSCI REMOTE SE, P2469, DOI 10.1109/IGARSS.2015.7326310
  • [10] A new fully convolutional neural network for semantic segmentation of polarimetric SAR imagery in complex land cover ecosystem
    Mohammadimanesh, Fariba
    Salehi, Bahram
    Mandianpari, Masoud
    Gill, Eric
    Molinier, Matthieu
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2019, 151 : 223 - 236