Assessment of ALOS PALSAR 50 m Orthorectified FBD Data for Regional Land Cover Classification by Support Vector Machines

From its launch in 2006, the phased array L-band synthetic aperture radar (PALSAR) onboard the advanced land observing satellite (ALOS) has acquired many dual-polarized (FBD) images with a 70-km swath width, aiming to produce spatially consistent coverage over tropical rainforest. This paper investigates the relevancy of PALSAR orthorectified FBD product at 50-m resolution for regional land cover classification by the support vector machines (SVM). Our test site is the Riau province, Sumatra island, Indonesia, known to hold vast area of natural peatland forest with an extreme biodiversity threatened by industrial deforestation. Since it is demonstrated the radiometric information (HH and HV channels) cannot be solely used to achieve a good classification, the spatial information in these orthorectified data is investigated. A new tool using the recursive feature elimination SVM-based process and the textural Haralick's parameters is introduced. The real contribution of textures within the land cover classification can be understood. A small set of textural parameters is determined at local scale while being optimal for the land cover discrimination. The SVM-based classifier is carried out across the whole Riau province and its results are compared with a Landsat-based estimation. The agreement is over 70% with six classes and 86% for the natural forest map. These results are remarkable since only one PALSAR FBD product is used and this assessment is performed on more than 40 million pixels. The results confirm the high potential of the PALSAR sensor for forest monitoring at regional, if not global scale.

[1]  Dirk H. Hoekman,et al.  Potential of airborne radar to support the assessment of land cover in a tropical rain forest environment , 1999 .

[2]  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..

[3]  Jon Atli Benediktsson,et al.  Spectral–Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[4]  F. Ulaby,et al.  Textural Infornation in SAR Images , 1986, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Dirk H. Hoekman.  Speckle ensemble statistics of logarithmically scaled data [radar] , 1991, IEEE Trans. Geosci. Remote. Sens..

[6]  J. Canadell,et al.  Tropical Forests and Climate Policy , 2007, Science.

[7]  Yumiko Uryu,et al.  Eco-floristic sectors and deforestation threats in Sumatra: identifying new conservation area network priorities for ecosystem-based land use planning , 2010, Biodiversity and Conservation.

[8]  Masanobu Shimada,et al.  PALSAR Radiometric and Geometric Calibration , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Masoud Nikravesh,et al.  Feature Extraction - Foundations and Applications , 2006, Feature Extraction.

[10]  Y. Laumonier,et al.  The Vegetation and Physiography of Sumatra , 1997, Geobotany.

[11]  F. Achard,et al.  Pan-tropical monitoring of deforestation , 2007 .

[12]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[13]  M. R. Bowen,et al.  Fire zones and the threat to the wetlands of Sumatra, Indonesia. , 2000 .

[14]  John W. Holt,et al.  Mapping land cover types in Amazon basin using 1 km JERS-1 mosaic , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[15]  Chris H. Q. Ding,et al.  Stable feature selection via dense feature groups , 2008, KDD.

[16]  Richard M. Lucas,et al.  Analysis by Wavelet Frames of Spatial Statistics in SAR Data for Characterizing Structural Properties of Forests , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Melanie Hilario,et al.  Knowledge and Information Systems , 2007 .

[18]  François Bourgeois,et al.  An extension of the Munkres algorithm for the assignment problem to rectangular matrices , 1971, CACM.

[19]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[20]  Masanobu Shimada,et al.  Ortho-Rectification and Slope Correction of SAR Data Using DEM and Its Accuracy Evaluation , 2010, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[21]  J. Swenson,et al.  Reference scenarios for deforestation and forest degradation in support of REDD: a review of data and methods , 2008 .

[22]  Sandra A. Brown,et al.  Monitoring and estimating tropical forest carbon stocks: making REDD a reality , 2007 .

[23]  Bernhard Schölkopf,et al.  Use of the Zero-Norm with Linear Models and Kernel Methods , 2003, J. Mach. Learn. Res..

[24]  George Kesidis,et al.  Margin-Maximizing Feature Elimination Methods for Linear and Nonlinear Kernel-Based Discriminant Functions , 2010, IEEE Transactions on Neural Networks.

[25]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[26]  Laurent Ferro-Famil,et al.  Estimation of Forest Structure, Ground, and Canopy Layer Characteristics From Multibaseline Polarimetric Interferometric SAR Data , 2010, IEEE Transactions on Geoscience and Remote Sensing.

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

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

[29]  Sergio Escalera,et al.  On the Decoding Process in Ternary Error-Correcting Output Codes , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Gallego Pinilla Francisco,et al.  Determination of World's Humid Tropical Deforestation Rates during the 1990's. Methodology and Results of the TREES-II Research Programme. , 2002 .

[31]  Martin Brown,et al.  Linear spectral mixture models and support vector machines for remote sensing , 2000, IEEE Trans. Geosci. Remote. Sens..

[32]  P. Atkinson,et al.  Relating SAR image texture to the biomass of regenerating tropical forests , 2005 .

[33]  J. J. Sanden.  Radar remote sensing to support tropical forest management. , 1997 .

[34]  Jong-Sen Lee,et al.  Target Detection and Texture Segmentation in Polarimetric SAR Images Using a Wavelet Frame: Theoretical Aspects , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[35]  S. Saatchi,et al.  Mapping land cover types in the Amazon Basin using 1 km JERS-1 mosaic , 2000 .

[36]  J. Munkres.  ALGORITHMS FOR THE ASSIGNMENT AND TRANSIORTATION tROBLEMS* , 1957 .

[37]  David A. Clausi,et al.  Rapid extraction of image texture by co-occurrence using a hybrid data structure , 2002 .

[38]  Manabu Watanabe,et al.  ALOS PALSAR: A Pathfinder Mission for Global-Scale Monitoring of the Environment , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[39]  Eric Rignot,et al.  Assessment of JERS-1 SAR for monitoring secondary vegetation in Amazonia: II. Spatial, temporal, and radiometric considerations for operational monitoring , 2002, International Journal of Remote Sensing.

[40]  J. V. Soares,et al.  Mapping deforestation and land use in Amazon rainforest by using SIR-C imagery , 1997 .

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