Multiple classifier systems for classification of multifrequency PolSAR images with limited training samples

ABSTRACT The aim of this article is to improve land-cover classification accuracy from multifrequency full-polarimetric synthetic aperture radar (PolSAR) observations using multiple classifier systems (MCSs) when limited training samples are available. Two types of popular MCSs, tree-based MCSs and neural-based MCSs, were compared with individual decision tree (DT) and neural network methods. Moreover, an objective majority voting (OMV) was proposed and compared with majority voting (MV) and weighted MV (WMV) to fuse the results of the MCSs. Experimental tests were performed on three benchmark PolSAR data sets with different frequencies (X, C, and L) over the San Francisco Bay, CA. The results indicated (1) tree-based MCSs and neural-based MCSs, in general, produced higher overall, producerʼs and userʼs accuracies than the related individual methods, i.e. DT and NN, with limited training samples; (2) tree-based MCSs were also often more accurate and much faster than neural-based MCSs; (3) regarding robustness, among the MCSs, random forest showed higher stability while bagging showed lower stability in the classification of three PolSAR data sets; (4) the OMV proposed in this article usually outperformed its competitors, i.e. MV and WMV; (5) the results obtained by the methods from the C-band data set were more accurate and more reliable than those obtained from the X- and L-band data sets.

[1]  Nathalie Pettorelli,et al.  Improving the accuracy of land cover classification in cloud persistent areas using optical and radar satellite image time series , 2020, Methods in Ecology and Evolution.

[2]  Boularbah Souissi,et al.  Optimal SVM Classification for Compact Polarimetric Data Using Stokes Parameters , 2014, J. Math. Model. Algorithms Oper. Res..

[3]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[4]  Lorenzo Bruzzone,et al.  An advanced system for the automatic classification of multitemporal SAR images , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Heather McNairn,et al.  Early season monitoring of corn and soybeans with TerraSAR-X and RADARSAT-2 , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[6]  Jiali Shang,et al.  Application of polarization signature to land cover scattering mechanism analysis and classification using multi-temporal C-band polarimetric RADARSAT-2 imagery. , 2017 .

[7]  M. Habibi,et al.  Classification of Polarimetric SAR Data Based on Object-Based Multiple Classifiers for Urban Land-Cover , 2016, Journal of the Indian Society of Remote Sensing.

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

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

[10]  Pascale C. Dubois,et al.  Measuring soil moisture with imaging radars , 1995, IEEE Trans. Geosci. Remote. Sens..

[11]  Heather McNairn,et al.  A particle swarm optimized kernel-based clustering method for crop mapping from multi-temporal polarimetric L-band SAR observations , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[12]  R. Polikar,et al.  Ensemble based systems in decision making , 2006, IEEE Circuits and Systems Magazine.

[13]  Jean-Claude Souyris,et al.  Support Vector Machine for Multifrequency SAR Polarimetric Data Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.

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

[15]  Lucy Marshall,et al.  Object-oriented crop classification using multitemporal ETM+ SLC-off imagery and random forest , 2013 .

[16]  Zhang Juan,et al.  Integrating color features in polarimetric SAR image classification , 2017 .

[17]  Matthieu Molinier,et al.  Polarimetric SAR Data in Land Cover Mapping in Boreal Zone , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[18]  M. Motagh,et al.  Classification of polarimetric SAR images using Support Vector Machines , 2011 .

[19]  Sukhendu Das,et al.  A Survey of Decision Fusion and Feature Fusion Strategies for Pattern Classification , 2010, IETE Technical Review.

[20]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[21]  Peijun Du,et al.  Polarimetric SAR image classification by Boosted Multiple-Kernel Extreme Learning Machines with polarimetric and spatial features , 2014 .

[22]  Farhad Samadzadegan,et al.  Classification of Polarimetric SAR Images Based on Optimum SVMs Classifier Using Bees Algorithm , 2012 .

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

[24]  Kun-Shan Chen,et al.  Classification of multifrequency polarimetric SAR imagery using a dynamic learning neural network , 1996, IEEE Trans. Geosci. Remote. Sens..

[25]  Hamid Ebadi,et al.  Improving the Accuracy of Land Cover Classification Using Fusion of Polarimetric SAR and Hyperspectral Images , 2016, Journal of the Indian Society of Remote Sensing.

[26]  Bardan Ghimire,et al.  An Evaluation of Bagging, Boosting, and Random Forests for Land-Cover Classification in Cape Cod, Massachusetts, USA , 2012 .

[27]  Giuseppe Satalino,et al.  Comparison of polarimetric SAR observables in terms of classification performance , 2008 .

[28]  Björn Waske,et al.  Classifying Multilevel Imagery From SAR and Optical Sensors by Decision Fusion , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[30]  Simon Yueh,et al.  Application of neural networks to radar image classification , 1994, IEEE Trans. Geosci. Remote. Sens..

[31]  Rudi Gens,et al.  Oceanographic Applications of SAR Remote Sensing , 2008 .

[32]  Liangpei Zhang,et al.  Polarimetric-Spatial Classification of SAR Images Based on the Fusion of Multiple Classifiers , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[33]  Yasser Maghsoudi,et al.  Polarimetric classification of Boreal forest using nonparametric feature selection and multiple classifiers , 2012, Int. J. Appl. Earth Obs. Geoinformation.

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

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

[36]  Simonetta Paloscia,et al.  The potential of multifrequency polarimetric SAR in assessing agricultural and arboreous biomass , 1997, IEEE Trans. Geosci. Remote. Sens..

[37]  J. Zyl,et al.  Bayesian classification of polarimetric SAR images using adaptive a priori probabilities , 1992 .

[38]  Wei Gao,et al.  Classification of Multi-Frequency Polarimetric SAR Images Based on Multi-Linear Subspace Learning of Tensor Objects , 2015, Remote. Sens..

[39]  Paolo Ferrazzoli,et al.  Experimental and model investigation on radar classification capability , 1999, IEEE Trans. Geosci. Remote. Sens..

[40]  Seiho Uratsuka,et al.  Season-long daily measurements of multifrequency (Ka, Ku, X, C, and L) and full-polarization backscatter signatures over paddy rice field and their relationship with biological variables , 2002 .

[41]  Xia Li,et al.  A three-component method for timely detection of land cover changes using polarimetric SAR images , 2015 .

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

[43]  Yoshio Yamaguchi,et al.  Land Cover Classification of Palsar Images by Knowledge Based Decision Tree Classifier and Supervised Classifiers Based on SAR Observables , 2011 .

[44]  Linlin Xu,et al.  A comparative study of different classification techniques for marine oil spill identification using RADARSAT-1 imagery , 2014 .

[45]  Dirk H. Hoekman,et al.  Unsupervised Full-Polarimetric SAR Data Segmentation as a Tool for Classification of Agricultural Areas , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[46]  Cuizhen Wang,et al.  Improved POLSAR Image Classification by the Use of Multi-Feature Combination , 2015, Remote. Sens..

[47]  K. Jezek,et al.  Unusual Radar Echoes from the Greenland Ice Sheet , 1993, Science.

[48]  Heather McNairn,et al.  Towards operational radar-only crop type classification: comparison of a traditional decision tree with a random forest classifier , 2012 .

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

[50]  Bruce Blanchard,et al.  Visible/Infrared/Microwave Agriculture Classification, Biomass, and Plant Height Algorithms , 1985, IEEE Transactions on Geoscience and Remote Sensing.

[51]  Wei Zhang,et al.  Multiple Classifier System for Remote Sensing Image Classification: A Review , 2012, Sensors.

[52]  Yasser Maghsoudi,et al.  Improving the Accuracy of Urban Land Cover Classification Using Radarsat-2 PolSAR Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[53]  Xin Niu,et al.  A Novel Contextual Classification Algorithm for Multitemporal Polarimetric SAR Data , 2014, IEEE Geoscience and Remote Sensing Letters.

[54]  Babak Mansouri,et al.  Comparison of the performance of L-band polarimetric parameters for land cover classification , 2012 .

[55]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[56]  M. Chakraborty,et al.  Discrimination between Babul plantations and Mustard crop using Polarimetric C- and L- band data , 2014, Journal of the Indian Society of Remote Sensing.

[57]  V. Alberga,et al.  A study of land cover classification using polarimetric SAR parameters , 2007 .

[58]  Heather McNairn,et al.  The Contribution of ALOS PALSAR Multipolarization and Polarimetric Data to Crop Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.