Fusion of PolSAR and PolInSAR data for land cover classification

Abstract The main research goal of this study is to investigate the complementarity and fusion of different frequencies (L- and P-band), polarimetric SAR (PolSAR) and polarimetric interferometric (PolInSAR) data for land cover classification. A large feature set was derived from each of these four modalities and a two-level fusion method was developed: Logistic regression (LR) as ‘feature-level fusion’ and the neural-network (NN) method for higher level fusion. For comparison, a support vector machine (SVM) was also applied. NN and SVM were applied on various combinations of the feature sets. The results show that for both NN and SVM, the overall accuracy for each of the fused sets is better than the accuracy for the separate feature sets. Moreover, that fused features from different SAR frequencies are complementary and adequate for land cover classification and that PolInSAR is complementary to PolSAR information and that both are essential for producing accurate land cover classification.

[1]  Melba M. Crawford,et al.  Fusion of airborne polarimetric and interferometric SAR for classification of coastal environments , 1999, IEEE Trans. Geosci. Remote. Sens..

[2]  Dirk H. Hoekman,et al.  Land cover type and biomass classification using AirSAR data for evaluation of monitoring scenarios in the Colombian Amazon , 2000, IEEE Trans. Geosci. Remote. Sens..

[3]  G. H. Rosenfield,et al.  A coefficient of agreement as a measure of thematic classification accuracy. , 1986 .

[4]  S. Cloude,et al.  Three-stage inversion process for polarimetric SAR interferometry , 2003 .

[5]  Jean-Claude Souyris,et al.  Use of the SVM Classification with Polarimetric SAR Data for Land Use Cartography , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[6]  Chih-Jen Lin,et al.  Combining SVMs with Various Feature Selection Strategies , 2006, Feature Extraction.

[7]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[8]  Gabriel Vasile,et al.  Feature detection in POLinSAR images by an interactive fuzzy fusion approach. Application to glacier monitoring , 2007 .

[9]  Christiaan Perneel,et al.  IMPROVED OBJECT RECOGNITION BY FUSION OF HYPERSPECTRAL AND SAR DATA , 2007 .

[10]  A. Farina,et al.  Fusion of radar images: state of art and perspective , 2001, 2001 CIE International Conference on Radar Proceedings (Cat No.01TH8559).

[11]  G. Mauris,et al.  Change detection in urban context with multitemporal ERS-SAR images by using data fusion approach , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[12]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[13]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[14]  P. Lombardo,et al.  Improved classification of SAR images by segmentation and fusion with optical images , 2002, RADAR 2002.

[15]  Isabelle Bloch,et al.  Multisensor Data Fusion for Spaceborne and Airborne Reduction of Mine Suspected Areas , 2007 .

[16]  R. Carande,et al.  Neural network classification with IFSAR and multispectral data fusion , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[17]  David G. Stork,et al.  Pattern Classification , 1973 .

[18]  Anil K. Jain,et al.  A Markov random field model for classification of multisource satellite imagery , 1996, IEEE Trans. Geosci. Remote. Sens..

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

[20]  A. Reigber,et al.  Data classification based on PolInSAR coherence shapes , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..

[21]  Gianfranco Fornaro,et al.  Imaging of Single and Double Scatterers in Urban Areas via SAR Tomography , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[22]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[23]  Ursula C. Benz,et al.  Supervised fuzzy analysis of single- and multichannel SAR data , 1999, IEEE Trans. Geosci. Remote. Sens..

[24]  N. Herold,et al.  An evaluation of radar texture for land use/cover extraction in varied landscapes , 2004 .

[25]  Jianshe Song,et al.  Fusion of Multi-band SAR Images Based on Contourlet Transform , 2006, 2006 IEEE International Conference on Information Acquisition.

[26]  E. Pottier,et al.  Fuzzy clustering and interpretation of fully polarimetric SAR data , 2001, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217).

[27]  Jean-Claude Souyris,et al.  Radar Polar Decomposition for Natural Surfaces Cartography , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[28]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[29]  D. Borghys,et al.  A SUPERVISED CLASSIFICATION OF MULTI-CHANNEL HIGH-RESOLUTION SAR DATA , 2007 .

[30]  Sebastiano B. Serpico,et al.  Fusion of multitemporal contextual information by neural networks for multisensor image classification , 2001, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217).

[31]  Jocelyn Chanussot,et al.  Assessment of Feature Selection Techniques for Support Vector Machine Classification of Satellite Imagery , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[32]  J. Zyl,et al.  Unsupervised classification of scattering behavior using radar polarimetry data , 1989 .

[33]  Anil K. Jain,et al.  Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images , 1994, IEEE Trans. Geosci. Remote. Sens..

[34]  Hsuan-Tien Lin.  A Study on Sigmoid Kernels for SVM and the Training of non-PSD Kernels by SMO-type Methods , 2005 .

[35]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[36]  Wooil M. Moon,et al.  Data fusion of multiple polarimetric SAR images using discrete wavelet transform (DWT) , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[37]  Wooil M. Moon,et al.  Decision level fusion of multi-frequency polarimetric SAR and optical data with Dempster-Shafer evidence theory , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[38]  Markus Törmä,et al.  Fusion of low resolution optical and high resolution SAR data for land cover classification , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[39]  Isabelle Bloch,et al.  SMART: Space and Airborne Mined Area Reduction Tools , 2003 .

[40]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[41]  A. Reigber,et al.  Evaluating PolInSAR parameter estimation using tomographic imaging results , 2005, European Radar Conference, 2005. EURAD 2005..

[42]  Stanley Lemeshow,et al.  Applied Logistic Regression, Second Edition , 1989 .

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

[44]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[45]  Richard R. Forster,et al.  Fusion of hyperspectral and radar data using the IHS transformation to enhance urban surface features , 2003 .

[46]  Aleksandra Pizurica,et al.  Supervised feature-based classification of multi-channel SAR images , 2006, Pattern Recognit. Lett..

[47]  S. Fukuda,et al.  Support vector machine classification of land cover: application to polarimetric SAR data , 2001, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217).

[48]  Shi Jun,et al.  Unsupervised classification of polarimetric SAR Image by Quad-tree Segment and SVM , 2007, 2007 1st Asian and Pacific Conference on Synthetic Aperture Radar.

[49]  Laurent Ferro-Famil,et al.  Classification and interpretation of polarimetric interferometric SAR data , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[50]  Bassel Solaiman,et al.  Multisensor data fusion using fuzzy concepts: application to land-cover classification using ERS-1/JERS-1 SAR composites , 1999, IEEE Trans. Geosci. Remote. Sens..

[51]  Luciano Alparone,et al.  Landsat ETM+ and SAR image fusion based on generalized intensity Modulation , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[52]  S. Cloude,et al.  Polarimetric Interferometry and Differential Interferometry , 2005 .

[53]  K. S. Kierein-Young.  The integration of optical and radar data to characterize mineralogy and morphology of surfaces in Death Valley, California, U.S.A. , 1997 .

[54]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[55]  J.J. van Zyl,et al.  Feature Utility In Polarimetric Radar Image Classificatiion , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

[56]  William L. Cameron,et al.  Simulated polarimetric signatures of primitive geometrical shapes , 1996, IEEE Trans. Geosci. Remote. Sens..

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

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

[59]  W. Holm,et al.  On radar polarization mixed target state decomposition techniques , 1988, Proceedings of the 1988 IEEE National Radar Conference.

[60]  Mihai Datcu,et al.  Road detection in dense urban areas using SAR imagery and the usefulness of multiple views , 2002, IEEE Trans. Geosci. Remote. Sens..

[61]  Anil K. Jain,et al.  Texture fusion and feature selection applied to SAR imagery , 1997, IEEE Trans. Geosci. Remote. Sens..

[62]  Michal Shimoni,et al.  Land Cover Feature Recognition by Fusion of POLSAR, PolInSAR and Optical Data , 2007 .

[63]  Paolo Gamba,et al.  Three-dimensional road network by fusion of polarimetric and interferometric SAR data , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[64]  J. Huynen.  Phenomenological theory of radar targets , 1970 .

[65]  Irena Hajnsek,et al.  PolInSAR analysis of X-band data over vegetated and urban areas , 2006, IEEE Transactions on Geoscience and Remote Sensing.

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

[67]  Laurent Ferro-Famil,et al.  A review of the applications of SAR polarimetry and polarimetric interferometry - an ESA funded study , 2003 .

[68]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[69]  E. Krogager.  New decomposition of the radar target scattering matrix , 1990 .