Wavelets for Urban Spatial Feature Discrimination: Comparisons with Fractal, Spatial Autocorrelation, and Spatial Co-Occurrence Approaches

Traditional image processing techniques have proven inadequate for urban mapping using high spatial resolution remotesensing images. This study examined and evaluated wavelet transforms for urban texture analysis and image classification using high spatial resolution ATLAS imagery. For the purpose of comparison and to evaluate the effectiveness of the wavelet approaches, two different fractal approaches (isarithm and triangular prism), spatial autocorrelation (Moran’s I and Geary’s C), and spatial co-occurrence matrix of the selected urban classes were examined using 65 � 65, 33 � 33, and 17 � 17 samples with a pixel size of 2.5 m. Results from this study suggest that a multi-band and multi-level wavelet approach can be used to drastically increase the classification accuracy. The fractal techniques did not provide satisfactory classification accuracy. Spatial autocorrelation and spatial co-occurrence techniques were found to be relatively effective when compared to the fractal approaches. It can be concluded that the wavelet transform approach is the most accurate of all four approaches.

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

[2]  R. M. Haralick,et al.  Textural features for image classification. IEEE Transaction on Systems, Man, and Cybernetics , 1973 .

[3]  Benoit B. Mandelbrot,et al.  Fractal Geometry of Nature , 1984 .

[4]  Richard W. Conners,et al.  A Theoretical Comparison of Texture Algorithms , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  J. Townshend,et al.  Terrain Analysis and Remote Sensing , 1982 .

[6]  D. Mark,et al.  Scale-dependent fractal dimensions of topographic surfaces: An empirical investigation, with applications in geomorphology and computer mapping , 1984 .

[7]  K. Clarke.  Computation of the fractal dimension of topographic surfaces using the triangular prism surface area method , 1985 .

[8]  Jams L. Cushnie.  The interactive effect of spatial resolution and degree of internal variability within land-cover types on classification accuracies , 1987 .

[9]  C. Woodcock,et al.  The use of variograms in remote sensing. I - Scene models and simulated images. II - Real digital images , 1988 .

[10]  G. Edwards,et al.  Texture Analysis Of Forest Regeneration Sites In High-resolution SAR Imagery , 1988, International Geoscience and Remote Sensing Symposium, 'Remote Sensing: Moving Toward the 21st Century'..

[11]  C. Woodcock,et al.  The use of variograms in remote sensing: I , 1988 .

[12]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  P. Gong,et al.  The use of structural information for improving land-cover classification accuracies at the rural-urban fringe. , 1990 .

[14]  D. Peddle,et al.  Image texture processing and data integration for surface pattern discrimination , 1991 .

[15]  P. Gong,et al.  Frequency-based contextual classification and gray-level vector reduction for land-use identification , 1992 .

[16]  Curtis E. Woodcock,et al.  Nested-hierarchical scene models and image segmentation , 1992 .

[17]  N. Lam,et al.  On the Issues of Scale, Resolution, and Fractal Analysis in the Mapping Sciences* , 1992 .

[18]  Sandeep Jaggi,et al.  Implementation and operation of three fractal measurement algorithms for analysis of remote-sensing data , 1993 .

[19]  K. Arai.  A classification method with a spatial-spectral variability , 1993 .

[20]  T. Fung,et al.  Spatial composition of spectral classes. A structural approach for image analysis of heterogeneous land-use and land-cover types , 1994 .

[21]  Peng Gong.  Reducing boundary effects in a kernel-based classifier , 1994 .

[22]  P. Burrough,et al.  A fractal approach to the classification of Mediterranean vegetation types in remotely sensed images , 1995 .

[23]  D. Quattrochi,et al.  Application of high-resolution thermal infrared remote sensing and GIS to assess the urban heat island effect , 1997 .

[24]  N. Lam,et al.  Environmental Assessment and Monitoring with ICAMS (Image Characterization and Modeling System) Using Multiscale Remote-Sensing Data , 1998 .

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

[26]  Chang-qing Zhu,et al.  Study of remote sensing image texture analysis and classification using wavelet , 1998 .

[27]  Ashfaq A. Khokhar,et al.  Vector-wavelet based scalable indexing and retrieval system for large color image archives , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[28]  N. Lam,et al.  Multi-Scale Fractal Analysis of Image Texture and Pattern , 1999 .

[29]  Aidong Zhang,et al.  A Multi-Resolution Content-Based Retrieval Approach for Geographic Images , 1999, GeoInformatica.

[30]  Martino Pesaresi,et al.  Texture Analysis for Urban Pattern Recognition Using Fine-resolution Panchromatic Satellite Imagery , 2000 .

[31]  R. Hall,et al.  Incorporating texture into classification of forest species composition from airborne multispectral images , 2000 .

[32]  S. Myint.  A Robust Texture Analysis and Classification Approach for Urban Land‐Use and Land‐Cover Feature Discrimination , 2001 .

[33]  N. Lam,et al.  An Evaluation of Fractal Methods for Characterizing Image Complexity , 2002 .

[34]  Soe Win Myint,et al.  An Evaluation of Four Different Wavelet Decomposition Procedures for Spatial Feature Discrimination in Urban Areas , 2002, Trans. GIS.

[35]  S. Myint,et al.  Fractal approaches in texture analysis and classification of remotely sensed data: Comparisons with spatial autocorrelation techniques and simple descriptive statistics , 2003 .

[36]  G..  A Theory for Multiresolution Signal Decomposition : The Wavelet Representation , 2004 .