Polarimetric SAR Classification Using Ridge Regression-Based Polarimetric-Spatial Feature Extraction

A polarimetric synthetic aperture radar (PolSAR) image classification is introduced in this work. The proposed method called as ridge regression-based polarimetric-spatial (RRPS) feature extraction generates polarimetric-spatial features with minimum overlapping and redundant information. To this end, each polarimetric-spatial channel of PolSAR data is represented through a ridge regression model using the farthest neighbors of that channel. The weights of the regression model compose the projection matrix for dimensionality reduction. The proposed RRPS method with a closed form solution has high performance in PolSAR image classification using small training sets.

[1]  Nelson D. A. Mascarenhas,et al.  SAR Speckle Nonlocal Filtering With Statistical Modeling of Haar Wavelet Coefficients and Stochastic Distances , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[2]  H. Ghassemian,et al.  Ridge regression-based feature extraction for hyperspectral data , 2015 .

[3]  Koray Kayabol,et al.  Pixel-Based Classification of SAR Images Using Feature Attribute Profiles , 2019, IEEE Geoscience and Remote Sensing Letters.

[4]  Lamei Zhang,et al.  Polarimetric SAR image classification based on contextual sparse representation , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[5]  H. Ghassemian,et al.  THE INVESTIGATION OF SENSITIVITY OF SVM CLASSIFIER RESPECT TO THE NUMBER OF FETURES AND THE NUMBER OF TRAINING SAMPLES , 2013 .

[6]  Zongben Xu,et al.  Polarimetric SAR Image Semantic Segmentation With 3D Discrete Wavelet Transform and Markov Random Field , 2020, IEEE Transactions on Image Processing.

[7]  Lamei Zhang,et al.  Object-Based Classification of PolSAR Images Based on Spatial and Semantic Features , 2020, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  Yasser Maghsoudi,et al.  Classification of Polarimetric SAR Images Based on Modeling Contextual Information and Using Texture Features , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Hui Xu,et al.  N-SAR: A New Multichannel Multimode Polarimetric Airborne SAR , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[10]  Jingjing Pei,et al.  Unsupervised classification of POLSAR data based on the polarimetric decomposition and the co-polarization ratio , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[11]  Hong Sun,et al.  Laplacian Eigenmaps-Based Polarimetric Dimensionality Reduction for SAR Image Classification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Alejandro C. Frery,et al.  Fully PolSAR image classification using machine learning techniques and reaction-diffusion systems , 2017, Neurocomputing.

[13]  Moncef Gabbouj,et al.  Multifrequency Polsar Image Classification Using Dual-Band 1D Convolutional Neural Networks , 2020, 2020 Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS).

[14]  Maryam Imani,et al.  Morphology-based structure-preserving projection for spectral-spatial feature extraction and classification of hyperspectral data , 2019, IET Image Process..

[15]  Sang-Eun Park,et al.  Automatic Urban Area Extraction From SAR Image Based on Morphological Operator , 2020 .

[16]  Qingfu Zhang,et al.  A class of learning algorithms for principal component analysis and minor component analysis , 2000, IEEE Trans. Neural Networks Learn. Syst..