Detection of built-up area expansion in ASTER and SAR images using conditional random fields

The heterogenous land-cover structure in built-up areas challenges existing classification methods. This study developed a method for detecting such areas from SAR and ASTER images using conditional random fields (CRFs). A feature selection approach and a novel data dependent term were designed and used to classify image blocks. A new approach of discriminating classes using variogram features was introduced. Mean, standard deviation and variogram slope features were used to characterize training areas including spatial dependencies of classes. The association potential was designed using support vector machines (SVMs) and the inverse of transformed Euclidean distance used as a data dependent term of the interaction potential. The latter maintained a stable accuracy when subjected to a variation of a smoothness parameter while preserving class boundaries and aggregating similar labels during classification. In this way, a discontinuity adaptive model that moderated smoothing given data evidence was obtained. The accuracy of detecting built-up areas using CRF exceeded that of Markov Random Fields (MRF), SVM and maximum likelihood classification (MLC) by 1.13%, 2.22% and 8.23% respectively. It also had the lowest fraction of false positives. Application of the method showed that built-up areas increased by 98.9 ha while 26.7 ha was converted from built-up to non-built-up areas. We conclude that the new procedure can be used to detect and monitor built-up area expansion; in this way it provides timely spatial information to urban planners and other relevant professionals.

[1]  Ping Zhong,et al.  Using Combination of Statistical Models and Multilevel Structural Information for Detecting Urban Areas From a Single Gray-Level Image , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[3]  Martial Hebert,et al.  Discriminative Random Fields , 2006, International Journal of Computer Vision.

[4]  Ping Zhong,et al.  A Multiple Conditional Random Fields Ensemble Model for Urban Area Detection in Remote Sensing Optical Images , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[5]  S. M. Jong,et al.  Remote Sensing Image Analysis: Including The Spatial Domain , 2011 .

[6]  James R. Anderson,et al.  A land use and land cover classification system for use with remote sensor data , 1976 .

[7]  Paul V. Bolstad,et al.  Coordinating methodologies for scaling landcover classifications from site-specific to global: Steps toward validating global map products , 1999 .

[8]  F. Rottensteiner,et al.  CLASSIFICATION OF SETTLEMENT AREAS IN REMOTE SENSING IMAGERY USING CONDITIONAL RANDOM FIELDS , 2010 .

[9]  Philip Lewis,et al.  Geostatistical classification for remote sensing: an introduction , 2000 .

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

[11]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[12]  Luis Gómez-Chova,et al.  Urban monitoring using multi-temporal SAR and multi-spectral data , 2006, Pattern Recognit. Lett..

[13]  M. Hodgson What Size Window for Image Classification? A Cognitive Perspective , 1998 .

[14]  Xue Chen,et al.  Urban areas detection based on conditional random field and multiscale textural features , 2009, International Symposium on Multispectral Image Processing and Pattern Recognition.

[15]  Florence Tupin,et al.  Fusion of Optical and SAR Images , 2010 .

[16]  D. Amarsaikhan,et al.  Fusing high-resolution SAR and optical imagery for improved urban land cover study and classification , 2010 .

[17]  Andreas Schenk,et al.  Delineation of Urban Footprints From TerraSAR-X Data by Analyzing Speckle Characteristics and Intensity Information , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Dengsheng Lu,et al.  Detection of urban expansion in an urban-rural landscape with multitemporal QuickBird images , 2010, Journal of applied remote sensing.

[19]  Ilkay Ulusoy,et al.  Generative versus discriminative methods for object recognition , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[20]  Kurt Hornik,et al.  Support Vector Machines in R , 2006 .

[21]  Xiaojun Yang,et al.  Urban remote sensing : monitoring, synthesis and modeling in the urban environment , 2011 .

[22]  Christian Heipke,et al.  Classification of multitemporal remote sensing data using Conditional Random Fields , 2010, 2010 IAPR Workshop on Pattern Recognition in Remote Sensing.

[23]  Sanjiv Kumar,et al.  Models for learning spatial interactions in natural images , 2004 .

[24]  Stan Z. Li Markov Random Field Modeling in Image Analysis , 2009, Advances in Pattern Recognition.

[25]  Alfred Stein,et al.  Quantification of the Effects of Land-Cover-Class Spectral Separability on the Accuracy of Markov-Random-Field-Based Superresolution Mapping , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[26]  R. Lark,et al.  Geostatistics for Environmental Scientists , 2001 .

[27]  Josef Strobl,et al.  What’s wrong with pixels? Some recent developments interfacing remote sensing and GIS , 2001 .

[28]  T. Esch,et al.  Urban remote sensing How can earth observation support the sustainable development of urban environments , 2010 .

[29]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[30]  Olaf Hellwich,et al.  Building Extraction from Polarimetric SAR Data using Mean Shift and Conditional Random Fields , 2008 .