Fusion of Support Vector Machines for Classification of Multisensor Data

The classification of multisensor data sets, consisting of multitemporal synthetic aperture radar data and optical imagery, is addressed. The concept is based on the decision fusion of different outputs. Each data source is treated separately and classified by a support vector machine (SVM). Instead of fusing the final classification outputs (i.e., land cover classes), the original outputs of each SVM discriminant function are used in the subsequent fusion process. This fusion is performed by another SVM, which is trained on the a priori outputs. In addition, two voting schemes are applied to create the final classification results. The results are compared with well-known parametric and nonparametric classifier methods, i.e., decision trees, the maximum-likelihood classifier, and classifier ensembles. The proposed SVM-based fusion approach outperforms all other approaches and significantly improves the results of a single SVM, which is trained on the whole multisensor data set.

[1]  Gustavo Camps-Valls,et al.  Composite kernels for hyperspectral image classification , 2006, IEEE Geoscience and Remote Sensing Letters.

[2]  Jon Atli Benediktsson,et al.  Decision Fusion for the Classification of Urban Remote Sensing Images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Johannes R. Sveinsson,et al.  Multiple classifiers applied to multisource remote sensing data , 2002, IEEE Trans. Geosci. Remote. Sens..

[4]  Jiao Licheng,et al.  Automatic model selection for support vector machines using heuristic genetic algorithm , 2006 .

[5]  Paul M. Mather,et al.  Pruning artificial neural networks: An example using land cover classification of multi-sensor images , 1999 .

[6]  Sebastiano B. Serpico,et al.  Classification of multisensor remote-sensing images by structured neural networks , 1995, IEEE Trans. Geosci. Remote. Sens..

[7]  Tong Lee,et al.  Probabilistic and Evidential Approaches for Multisource Data Analysis , 1987, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Chih-Jen Lin,et al.  Radius Margin Bounds for Support Vector Machines with the RBF Kernel , 2002, Neural Computation.

[9]  IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 34. NO. 4, JULY 1996 Universal Multifractal Scaling of Synthetic , 1996 .

[10]  Paul M. Mather,et al.  An assessment of the effectiveness of decision tree methods for land cover classification , 2003 .

[11]  Paul M. Mather,et al.  Some issues in the classification of DAIS hyperspectral data , 2006 .

[12]  P. Swain,et al.  Neural Network Approaches Versus Statistical Methods In Classification Of Multisource Remote Sensing Data , 1990 .

[13]  Alan H. Strahler,et al.  Maximizing land cover classification accuracies produced by decision trees at continental to global scales , 1999, IEEE Trans. Geosci. Remote. Sens..

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

[15]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[16]  James A. Bucklew,et al.  Support vector machines and the multiple hypothesis test problem , 2001, IEEE Trans. Signal Process..

[17]  Johannes R. Sveinsson,et al.  Support vector machines in multisource classification , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[18]  D. Ducrot,et al.  Land cover discrimination potential of radar multitemporal series and optical multispectral images in a Mediterranean cultural landscape , 2004 .

[19]  Johannes R. Sveinsson,et al.  Hybrid consensus theoretic classification , 1996, IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium.

[20]  Björn Waske,et al.  Random Feature Selection for Decision Tree Classification of Multi-temporal SAR Data , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[21]  Xavier Blaes,et al.  Efficiency of crop identification based on optical and SAR image time series , 2005 .

[22]  Brian M. Steele,et al.  Combining Multiple Classifiers: An Application Using Spatial and Remotely Sensed Information for Land Cover Type Mapping , 2000 .

[23]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[24]  Jon Atli Benediktsson,et al.  Consensus theoretic classification methods , 1992, IEEE Trans. Syst. Man Cybern..

[25]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[26]  Jon Atli Benediktsson,et al.  A Combined Support Vector Machines Classification Based on Decision Fusion , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[27]  David A. Landgrebe,et al.  Signal Theory Methods in Multispectral Remote Sensing , 2003 .

[28]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[29]  Paul M. Mather,et al.  Support vector machines for classification in remote sensing , 2005 .

[30]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[31]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[32]  Jon Atli Benediktsson,et al.  Classification of multisource and hyperspectral data based on decision fusion , 1999, IEEE Trans. Geosci. Remote. Sens..

[33]  Giles M. Foody,et al.  A relative evaluation of multiclass image classification by support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Sassan Saatchi,et al.  The use of decision tree and multiscale texture for classification of JERS-1 SAR data over tropical forest , 2000, IEEE Trans. Geosci. Remote. Sens..

[35]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[36]  Henri Laur,et al.  Derivation of the backscattering coefficient s0 in ESA ERS SAR PRI products , 1996 .

[37]  Guoliang Fan,et al.  Automatic CRP mapping using nonparametric machine learning approaches , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[39]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[40]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[41]  D. Michelson.  Comparison of Algorithms for Classifying Swedish Landcover Using Landsat TM and ERS-1 SAR Data , 2000 .

[42]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .