Texture-based classification of ground-penetrating radar images

Image texture is one of the key features used for the interpretation of radar facies in ground-penetrating radar (GPR) data. Establishing quantitative measures of texture is therefore a critical step in the effective development of advanced techniques for the interpretation of GPR images. This study presents the first effort to evaluate whether different measures of a GPR image capture the features of the data that, when coupled with a neural network classifier, are able to reproduce a human interpretation. The measures compared in this study are instantaneous amplitude and frequency, as well as the variance, covariance, Fourier-Mellin transform, R-transform, and principle components (PCs) determined for a window of radar data. A 50-MHz GPR section collected over the William River delta in Saskatchewan, Canada, is used for the analysis. We found that measures describing the local spatial structure of the GPR image (i.e., covariance, Fourier-Mellin, R-transform, and PCs) were able to reproduce human interp...

[1]  C. H. Chen,et al.  Handbook of Pattern Recognition and Computer Vision , 1993 .

[2]  D. FitzGerald,et al.  Application of ground penetrating radar in coastal stratigraphic studies , 1994 .

[3]  Paul J. Curran,et al.  Remote sensing: Using the spatial domain , 2001, Environmental and Ecological Statistics.

[4]  JEFFREY WOOD,et al.  Invariant pattern recognition: A review , 1996, Pattern Recognit..

[5]  Dengliang Gao,et al.  Texture model regression for effective feature discrimination: Application to seismic facies visualization and interpretation , 2004 .

[6]  R. Bracewell.  The Fourier Transform and Its Applications , 1966 .

[7]  R. Reyment,et al.  Statistics and Data Analysis in Geology. , 1988 .

[8]  F. P. Haeni,et al.  Application of Ground‐Penetrating‐Radar Methods in Hydrogeologie Studies , 1991 .

[9]  R. A. Overmeeren,et al.  Radar facies of unconsolidated sediments in The Netherlands: A radar stratigraphy interpretation method for hydrogeology , 1998 .

[10]  G. McMechan,et al.  Prediction of 3-D fluid permeability and mudstone distributions from ground-penetrating radar (GPR) attributes: Example from the Cretaceous Ferron Sandstone Member, east-central Utah , 2002 .

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

[12]  Ajai Jain,et al.  The Handbook of Pattern Recognition and Computer Vision , 1993 .

[13]  A. Neal.  Ground-penetrating radar and its use in sedimentology: principles, problems and progress , 2004 .

[14]  B. N. Chatterji,et al.  An FFT-based technique for translation, rotation, and scale-invariant image registration , 1996, IEEE Trans. Image Process..

[15]  Thierry Coléou,et al.  Interpreter's Corner—Unsupervised seismic facies classification: A review and comparison of techniques and implementation , 2003 .

[16]  K. W. Cattermole.  The Fourier Transform and its Applications , 1965 .

[17]  M. Taner,et al.  Complex seismic trace analysis , 1979 .

[18]  Thomas Aigner,et al.  Towards realistic aquifer models: Three-dimensional georadar surveys of Quaternary gravel deltas (Si , 1999 .

[19]  Remke L. Van Dam,et al.  Identifying causes of ground‐penetrating radar reflections using time‐domain reflectometry and sedimentological analyses , 2000 .

[20]  H. Jol,et al.  Ground penetrating radar: 2-D and 3-D subsurface imaging of a coastal barrier spit, Long Beach, WA, USA , 2003 .

[21]  J. Caers,et al.  Stochastic estimation of facies using ground penetrating radar data , 2003 .

[22]  Johan Alexander Huisman,et al.  Iron oxides as a cause of GPR reflections , 2002 .

[23]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[24]  G. Kaminsky,et al.  Annual Layers Revealed by GPR in the Subsurface of a Prograding Coastal Barrier, Southwest Washington, U.S.A. , 2004 .

[25]  Christian Regli,et al.  Interpretation of drill-core and georadar data of coarse gravel deposits , 2002 .

[26]  Harry M. Jol,et al.  Ground penetrating radar of northern lacustrine deltas , 1991 .

[27]  Harry M. Jol,et al.  Ground penetrating radar antennae frequencies and transmitter powers compared for penetration depth, resolution and reflection continuity1 , 1995 .

[28]  D. Daniels.  Ground Penetrating Radar , 2005 .

[29]  P. Huggenberger,et al.  Three-dimensional geometry of fluvial gravel deposits from GPR reflection patterns; a comparison of results of three different antenna frequencies , 1994 .

[30]  Alan G. Green,et al.  Using two- and three-dimensional georadar methods to characterize glaciofluvial architecture , 1999 .

[31]  Fritz Stauffer,et al.  A numerical three‐dimensional conditioned/unconditioned stochastic facies type model applied to a remediation well system , 1998 .

[32]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[33]  Harry M. Jol,et al.  A comparison of the correlation structure in GPR images of deltaic and barrier‐spit depositional environments , 2000 .

[34]  Xianlin Ma,et al.  Modeling Conditional Distributions of Facies from Seismic Using Neural Nets , 2002 .

[35]  Rosemary Knight,et al.  GEOSTATISTICAL ANALYSIS OF GROUND-PENETRATING RADAR DATA : A MEANS OF DESCRIBING SPATIAL VARIATION IN THE SUBSURFACE , 1998 .

[36]  Derald G. Smith,et al.  Sedimentology of an Upper-Mesotidal (3.7 M) Holocene Barrier, Willapa Bay, SW Washington, U.S.A. , 1999 .