Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network

被引:45
作者
Cao, Yice [1 ]
Wu, Yan [1 ]
Zhang, Peng [2 ]
Liang, Wenkai [1 ]
Li, Ming [2 ]
机构
[1] Xidian Univ, Sch Elect Engn, Remote Sensing Image Proc & Fusion Grp, Xian 710071, Shaanxi, Peoples R China
[2] Xidian Univ, Natl Lab Radar Signal Proc, Xian 710071, Shaanxi, Peoples R China
基金
中国国家自然科学基金;
关键词
complex-valued deep fully convolutional neural network (CV-FCN); polarimetric synthetic aperture radar (PolSAR) image classification; pixel-level labeling; POLARIMETRIC SAR IMAGERY; NEURAL-NETWORK; SEMANTIC SEGMENTATION; LAND CLASSIFICATION;
D O I
10.3390/rs11222653
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Although complex-valued (CV) neural networks have shown better classification results compared to their real-valued (RV) counterparts for polarimetric synthetic aperture radar (PolSAR) classification, the extension of pixel-level RV networks to the complex domain has not yet thoroughly examined. This paper presents a novel complex-valued deep fully convolutional neural network (CV-FCN) designed for PolSAR image classification. Specifically, CV-FCN uses PolSAR CV data that includes the phase information and uses the deep FCN architecture that performs pixel-level labeling. The CV-FCN architecture is trained in an end-to-end scheme to extract discriminative polarimetric features, and then the entire PolSAR image is classified by the trained CV-FCN. Technically, for the particularity of PolSAR data, a dedicated complex-valued weight initialization scheme is proposed to initialize CV-FCN. It considers the distribution of polarization data to conduct CV-FCN training from scratch in an efficient and fast manner. CV-FCN employs a complex downsampling-then-upsampling scheme to extract dense features. To enrich discriminative information, multi-level CV features that retain more polarization information are extracted via the complex downsampling scheme. Then, a complex upsampling scheme is proposed to predict dense CV labeling. It employs the complex max-unpooling layers to greatly capture more spatial information for better robustness to speckle noise. The complex max-unpooling layers upsample the real and the imaginary parts of complex feature maps based on the max locations maps retained from the complex downsampling scheme. In addition, to achieve faster convergence and obtain more precise classification results, a novel average cross-entropy loss function is derived for CV-FCN optimization. Experiments on real PolSAR datasets demonstrate that CV-FCN achieves better classification performance than other state-of-art methods.
引用
收藏
页数:29
相关论文
共 49 条
  • [1] Classification comparisons between dual-pol, compact polarimetric and quad-pol SAR imagery
    Ainsworth, T. L.
    Kelly, J. P.
    Lee, J. -S.
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2009, 64 (05) : 464 - 471
  • [2] Three-Component Model-Based Decomposition for Polarimetric SAR Data
    An, Wentao
    Cui, Yi
    Yang, Jian
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2010, 48 (06): : 2732 - 2739
  • [3] [Anonymous], 2015, IEEE I CONF COMP VIS, DOI DOI 10.1109/ICCV.2015.123
  • [4] [Anonymous], 2011, POLARIMETRIC RADAR I
  • [5] Adaptive Model-Based Decomposition of Polarimetric SAR Covariance Matrices
    Arii, Motofumi
    van Zyl, Jakob J.
    Kim, Yunjin
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (03): : 1104 - 1113
  • [6] A Graph-Based Semisupervised Deep Learning Model for PolSAR Image Classification
    Bi, Haixia
    Sun, Jian
    Xu, Zongben
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (04): : 2116 - 2132
  • [7] The use of fully polarimetric information for the fuzzy neural classification of SAR images
    Chen, CT
    Chen, KS
    Lee, JS
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (09): : 2089 - 2100
  • [8] An entropy based classification scheme for land applications of polarimetric SAR
    Cloude, SR
    Pottier, E
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1997, 35 (01): : 68 - 78
  • [9] A review of target decomposition theorems in radar polarimetry
    Cloude, SR
    Pottier, E
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1996, 34 (02): : 498 - 518
  • [10] An Unsupervised Classification Approach for Polarimetric SAR Data Based on the Chernoff Distance for Complex Wishart Distribution
    Dabboor, Mohammed
    Collins, Michael J.
    Karathanassi, Vassilia
    Braun, Alexander
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (07): : 4200 - 4213