Improved POLSAR Image Classification by the Use of Multi-Feature Combination

Polarimetric SAR (POLSAR) provides a rich set of information about objects on land surfaces. However, not all information works on land surface classification. This study proposes a new, integrated algorithm for optimal urban classification using POLSAR data. Both polarimetric decomposition and time-frequency (TF) decomposition were used to mine the hidden information of objects in POLSAR data, which was then applied in the C5.0 decision tree algorithm for optimal feature selection and classification. Using a NASA/JPL AIRSAR POLSAR scene as an example, the overall accuracy and kappa coefficient of the proposed method reached 91.17% and 0.90 in the L-band, much higher than those achieved by the commonly applied Wishart supervised classification that were 45.65% and 0.41. Meantime, the overall accuracy of the proposed method performed well in both C- and P-bands. Polarimetric decomposition and TF decomposition all proved useful in the process. TF information played a great role in delineation between urban/built-up areas and vegetation. Three polarimetric features (entropy, Shannon entropy, T11 Coherency Matrix element) and one TF feature (HH intensity of coherence) were found most helpful in urban areas classification. This study indicates that the integrated use of polarimetric decomposition and TF decomposition of POLSAR data may provide improved feature extraction in heterogeneous urban areas.

[1]  Eric Pottier,et al.  A review of target decomposition theorems in radar polarimetry , 1996, IEEE Trans. Geosci. Remote. Sens..

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

[3]  Hiroyoshi Yamada,et al.  Four-component scattering model for polarimetric SAR image decomposition , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Laurence A. Nafie,et al.  Vibrational Optical Activity: Principles and Applications , 2011 .

[5]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[6]  J. Kong,et al.  Identification of Terrain Cover Using the Optimum Polarimetric Classifier , 2012 .

[7]  Hongwei Liu,et al.  Target spatial and frequency scattering diversity property for diversity MIMO radar , 2011, Signal Process..

[8]  Hiroyoshi Yamada,et al.  A four-component decomposition of POLSAR images based on the coherency matrix , 2006, IEEE Geoscience and Remote Sensing Letters.

[9]  Fawwaz T. Ulaby,et al.  The Bayesian hierarchical classifier (BHC) and its application to short vegetation using multifrequency polarimetric SAR , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Sulin Pang,et al.  C5.0 Classification Algorithm and Application on Individual Credit Evaluation of Banks , 2009 .

[11]  Seisuke Fukuda,et al.  A wavelet-based texture feature set applied to classification of multifrequency polarimetric SAR images , 1999, IEEE Trans. Geosci. Remote. Sens..

[12]  P. Réfrégier,et al.  Shannon entropy of partially polarized and partially coherent light with Gaussian fluctuations. , 2006, Journal of the Optical Society of America. A, Optics, image science, and vision.

[13]  D. Rajan Probability, Random Variables, and Stochastic Processes , 2017 .

[14]  Konstantinos P. Papathanassiou,et al.  Polarimetric SAR interferometry , 1998, IEEE Trans. Geosci. Remote. Sens..

[15]  Xia Li,et al.  A novel algorithm for land use and land cover classification using RADARSAT-2 polarimetric SAR data , 2012 .

[16]  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.

[17]  Thomas L. Ainsworth,et al.  Unsupervised classification using polarimetric decomposition and the complex Wishart classifier , 1999, IEEE Trans. Geosci. Remote. Sens..

[18]  W. Loh,et al.  SPLIT SELECTION METHODS FOR CLASSIFICATION TREES , 1997 .

[19]  Gonzalo Pajares,et al.  Improving the Wishart Synthetic Aperture Radar image classifications through Deterministic Simulated Annealing , 2011 .

[20]  Laurent Ferro-Famil,et al.  Nonstationary natural media analysis from polarimetric SAR data using a two-dimensional time-frequency decomposition approach , 2005 .

[21]  J. J. Gil,et al.  Polarimetric characterization of light and media - Physical quantities involved in polarimetric phenomena , 2007, 2002.04105.

[22]  Motoyuki Sato,et al.  PolInSAR Complex Coherence Estimation Based on Covariance Matrix Similarity Test , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Yang Wang,et al.  Feature‐selection ability of the decision‐tree algorithm and the impact of feature‐selection/extraction on decision‐tree results based on hyperspectral data , 2008, International Journal of Remote Sensing.

[24]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  E. Pottier,et al.  The conformity coefficient or how to explore the scattering behaviour from compact polarimetry mode , 2009, 2009 IEEE Radar Conference.

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

[27]  Turker Ince,et al.  Unsupervised classification of polarimetric SAR image with dynamic clustering: An image processing approach , 2010, Adv. Eng. Softw..

[28]  Mark A. Friedl,et al.  Using prior probabilities in decision-tree classification of remotely sensed data , 2002 .

[29]  A. Frery,et al.  Multifrequency Full Polarimetric SAR Classification with Multiple Sources of Statistical Evidence , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[30]  Irena Hajnsek,et al.  Polarimetric and interferometric characterization of coherent scatterers in urban areas , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Marc Acheroy,et al.  Fusion of PolSAR and PolInSAR data for land cover classification , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[32]  João Roberto dos Santos,et al.  Land Use and Land Cover Mapping in the Brazilian Amazon Using Polarimetric Airborne P-Band SAR Data , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Eric Pottier,et al.  Quantitative comparison of classification capability: fully polarimetric versus dual and single-polarization SAR , 2001, IEEE Trans. Geosci. Remote. Sens..

[34]  Stephen L. Durden,et al.  A three-component scattering model for polarimetric SAR data , 1998, IEEE Trans. Geosci. Remote. Sens..

[35]  Wang Jun,et al.  A Novel Unsupervised Classifier of Polarimetric SAR Images , 2011 .

[36]  Laurent Ferro-Famil,et al.  Scene characterization using subaperture polarimetric SAR data , 2003, IEEE Trans. Geosci. Remote. Sens..

[37]  Gonzalo Pajares,et al.  Improving Wishart Classification of Polarimetric SAR Data Using the Hopfield Neural Network Optimization Approach , 2012, Remote. Sens..

[38]  Cuizhen Wang,et al.  Improved Building Extraction With Integrated Decomposition of Time-Frequency and Entropy-Alpha Using Polarimetric SAR Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[39]  Laurent Ferro-Famil,et al.  Statistical Classification for Heterogeneous Polarimetric SAR Images , 2011, IEEE Journal of Selected Topics in Signal Processing.

[40]  C. Lee,et al.  Georegistration of airborne hyperspectral image data , 2001, IEEE Trans. Geosci. Remote. Sens..

[41]  Ron Kwok,et al.  Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution , 1994 .

[42]  Jinfei Wang,et al.  Texture evaluation of RADARSAT imagery for wetland mapping , 2002 .

[43]  A. Reigber,et al.  RAT ( Radar Tools ) : A free SAR image analysis software package , 2004 .