Deep Fuzzy Graph Convolutional Networks for PolSAR Imagery Pixelwise Classification

Pixelwise classification plays an important role for image interpretation. The remote sensing images, especially polarimetric synthetic aperture radar (PolSAR), have provided wide applications for both military and civilian users regardless of weather or lighting conditions. However, the classification of heterogeneous imagery is still challenging. In this article, we propose a novel deep fuzzy graph convolutional network (DFGCN) for pixelwise classification of PolSAR imagery. Inspired by the fuzzy logic, the imagery (i.e., a reflection of the backscattering of the ground) is represented by a fuzzy graph, whose node is associated with a feature vector, and fuzzy weights denoting the similarity degrees between nodes are defined by using both feature distance and spatial relation. We also construct a new graph residual module stacking multiple residual layers to extend the depth of our fuzzy graph network. Moreover, we present a graph shrinking strategy to reduce the graph size for training and predicting the labels of large-scale PolSAR imagery, which can cut down the computational cost. The experimental results on various real-world PolSAR datasets indicate that DFGCN dramatically enhances classification accuracies on both heterogeneous and homogeneous regions with limited labeled pixels compared with the state-of-the-art methods.

[1]  Holger H. Hoos,et al.  A survey on semi-supervised learning , 2019, Machine Learning.

[2]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[3]  Serkan Kiranyaz,et al.  Integrating Color Features in Polarimetric SAR Image Classification , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[5]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[6]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Jian Yang,et al.  The boosting algorithm with application to polarimetric SAR image classification , 2007, 2007 1st Asian and Pacific Conference on Synthetic Aperture Radar.

[8]  Zongben Xu,et al.  Unsupervised PolSAR Image Classification Using Discriminative Clustering , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Eric W. Gill,et al.  A new fully convolutional neural network for semantic segmentation of polarimetric SAR imagery in complex land cover ecosystem , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[10]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[11]  Hong Sun,et al.  Polarimetric SAR Image Classification Using Multifeatures Combination and Extremely Randomized Clustering Forests , 2010, EURASIP J. Adv. Signal Process..

[12]  Shuiping Gou,et al.  Semisupervised Feature Extraction With Neighborhood Constraints for Polarimetric SAR Classification , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[13]  Shuiping Gou,et al.  Semi-Supervised Tensorial Locally Linear Embedding for Feature Extraction Using PolSAR Data , 2018, IEEE Journal of Selected Topics in Signal Processing.

[14]  E. Pottier,et al.  Polarimetric Radar Imaging: From Basics to Applications , 2009 .

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Fang Liu,et al.  POL-SAR Image Classification Based on Wishart DBN and Local Spatial Information , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Shuai Liu,et al.  Terrain classification based on spatial multi-attribute graph using Polarimetric SAR data , 2018, Appl. Soft Comput..

[18]  Yun Fu,et al.  Residual Dense Network for Image Super-Resolution , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[19]  Shuang Wang,et al.  Fuzzy Superpixels for Polarimetric SAR Images Classification , 2018, IEEE Transactions on Fuzzy Systems.

[20]  Carmine Clemente,et al.  Detecting Covariance Symmetries in Polarimetric SAR Images , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Shuyuan Yang,et al.  Fast Semisupervised Classification Using Histogram-Based Density Estimation for Large-Scale Polarimetric SAR Data , 2019, IEEE Geoscience and Remote Sensing Letters.

[23]  Zongben Xu,et al.  An Active Deep Learning Approach for Minimally Supervised PolSAR Image Classification , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[24]  Shuyuan Yang,et al.  Large Polarimetric SAR Data Semi-Supervised Classification With Spatial-Anchor Graph , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[25]  Zongben Xu,et al.  A Graph-Based Semisupervised Deep Learning Model for PolSAR Image Classification , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Mohammed Otair,et al.  Approximate k-nearest neighbour based spatial clustering using k-d tree , 2013, ArXiv.

[27]  Robert Jenssen,et al.  Spectral Clustering of Polarimetric SAR Data With Wishart-Derived Distance Measures , 2007 .

[28]  Maoguo Gong,et al.  Sparse Manifold-Regularized Neural Networks for Polarimetric SAR Terrain Classification , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Shuiping Gou,et al.  Fast Classification for Large Polarimetric SAR Data Based on Refined Spatial-Anchor Graph , 2017, IEEE Geoscience and Remote Sensing Letters.

[30]  Eric Pottier,et al.  An entropy based classification scheme for land applications of polarimetric SAR , 1997, IEEE Trans. Geosci. Remote. Sens..

[31]  Jong-Sen Lee,et al.  Polarimetric SAR speckle filtering and its implication for classification , 1999, IEEE Trans. Geosci. Remote. Sens..

[32]  Gabriel Vasile,et al.  Coherency Matrix Estimation of Heterogeneous Clutter in High-Resolution Polarimetric SAR Images , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Thomas L. Ainsworth,et al.  Unsupervised classification of polarimetric synthetic aperture Radar images using fuzzy clustering and EM clustering , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Antonio De Maio,et al.  A Robust Framework for Covariance Classification in Heterogeneous Polarimetric SAR Images and Its Application to L-Band Data , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[35]  Xiao-Ming Wu,et al.  Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning , 2018, AAAI.

[36]  Yoshua Bengio,et al.  Gradient-Based Optimization of Hyperparameters , 2000, Neural Computation.

[37]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[38]  Shuiping Gou,et al.  Polarimetric SAR Feature Extraction With Neighborhood Preservation-Based Deep Learning , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[39]  Mingsheng Liao,et al.  Texture Classification of PolSAR Data Based on Sparse Coding of Wavelet Polarization Textons , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Wenxian Yu,et al.  Superpixel-Based Classification With an Adaptive Number of Classes for Polarimetric SAR Images , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Danilo Orlando,et al.  Polarimetric Covariance Eigenvalues Classification in SAR Images , 2019, IEEE Geoscience and Remote Sensing Letters.

[42]  Torbjørn Eltoft,et al.  Model-Based Polarimetric Decomposition With Higher Order Statistics , 2019, IEEE Geoscience and Remote Sensing Letters.

[43]  Bernard Ghanem,et al.  DeepGCNs: Can GCNs Go As Deep As CNNs? , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[44]  Yu Zhou,et al.  Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks , 2016, IEEE Geoscience and Remote Sensing Letters.

[45]  Bernard Ghanem,et al.  Can GCNs Go as Deep as CNNs? , 2019, ArXiv.

[46]  Shuang Wang,et al.  Multilayer feature learning for polarimetric synthetic radar data classification , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.