Physics-Based Detection of Subpixel Targets in Hyperspectral Imagery

Abstract : Hyperspectral imagery provides the ability to detect targets that are smaller than the size of a pixel. They provide this ability by measuring the reflection and absorption of light at different wave lengths creating a spectral signature for each pixel in the image. This spectral signature contains information about the different materials within the pixel; therefore, the challenge in subpixel target detection lies in separating the targets spectral signature from competing background signatures. Most research has approached this problem in a purely statistical manner. Our approach fuses statistical signal processing techniques with the physics of reflectance spectroscopy and radiative transfer theory. Using this approach, we provide novel algorithms for all aspects of subpixel detection from parameter estimation to threshold determination. Characterization of the target and background spectral signatures is a key part of subpixel detection. We develop an algorithm to generate target signatures based onradiative transfer theory using only the image and a reference signature without the need for calibration, weather information, or source-target-receiver geometries. For background signatures, our work identifies that even slight estimation errors in the number of background signatures can severely degrade detection performance. To this end, we present a new method to estimate the number of background signatures specifically for subpixel target detection. At the core of the dissertation is the development of two hybrid detectors which fuse spectroscopy with statistical hypothesis testing. Our results show that the hybrid detectors provide improved performance in three different ways: insensitivity to the number of background signatures, improved detection performance, and consistent performance across multiple images leading to improved receiver operating characteristic curves. Lastly, we present a novel adaptive threshold estimate via extreme value theory.

[1]  Marco Gianinetto,et al.  The development of Superspectral approaches for the improvement of land cover classification , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[2]  B. Hapke.  Theory of reflectance and emittance spectroscopy , 1993 .

[3]  F. Kruse.  Use of airborne imaging spectrometer data to map minerals associated with hydrothermally altered rocks in the northern grapevine mountains, Nevada, and California , 1988 .

[4]  Wallace M. Porter,et al.  The airborne visible/infrared imaging spectrometer (AVIRIS) , 1993 .

[5]  Russell M. Mersereau,et al.  On the impact of covariance contamination for adaptive detection in hyperspectral imaging , 2005, IEEE Signal Processing Letters.

[6]  J. Boardman,et al.  Mapping target signatures via partial unmixing of AVIRIS data: in Summaries , 1995 .

[7]  Antonio J. Plaza,et al.  Spatial/spectral endmember extraction by multidimensional morphological operations , 2002, IEEE Trans. Geosci. Remote. Sens..

[8]  David Gillis,et al.  New improvements in the ORASIS algorithm , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[9]  Dimitris Manolakis,et al.  Realistic matched filter performance prediction for hyperspectral target detection , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[10]  E. J. Kelly.  An Adaptive Detection Algorithm , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[11]  E. Gumbel,et al.  Statistics of extremes , 1960 .

[12]  Chein-I Chang,et al.  Automatic spectral target recognition in hyperspectral imagery , 2003 .

[13]  S. Roberts.  Novelty detection using extreme value statistics , 1999 .

[14]  Alan P. Schaum,et al.  Application of stochastic mixing models to hyperspectral detection problems , 1997, Defense, Security, and Sensing.

[15]  M. Fréchet.  Sur la loi de probabilité de l'écart maximum , 1928 .

[16]  Yoram J. Kaufman,et al.  Solution of the equation of radiative transfer for remote sensing over nonuniform surface reflectivity , 1982 .

[17]  Chein-I Chang,et al.  Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[18]  John Fisher,et al.  Hyperspectral analysis and target detection system for the Adaptive Spectral Reconnaissance Program (ASRP) , 1998, Defense, Security, and Sensing.

[19]  Gregory Asner,et al.  Endmember bundles: a new approach to incorporating endmember variability into spectral mixture analysis , 2000, IEEE Trans. Geosci. Remote. Sens..

[20]  Louis L. Scharf,et al.  Adaptive subspace detectors , 2001, IEEE Trans. Signal Process..

[21]  Laurence B. Milstein,et al.  Robust detection using extreme-value theory , 1969, IEEE Trans. Inf. Theory.

[22]  Megan M. Lewis,et al.  Discrimination of arid vegetation with airborne multispectral scanner hyperspectral imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[23]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..

[24]  D. Landgrebe.  Multispectral land sensing: where from, where to? , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[25]  Rama Chellappa,et al.  Kernel fully constrained least squares abundance estimates , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[26]  J.S. Sadowsky,et al.  On large deviations theory and asymptotically efficient Monte Carlo estimation , 1990, IEEE Trans. Inf. Theory.

[27]  James A. Bucklew.  The Blind Simulation Problem and Regenerative Processes , 1998, IEEE Trans. Inf. Theory.

[28]  A. Goetz,et al.  Column atmospheric water vapor and vegetation liquid water retrievals from Airborne Imaging Spectrometer data , 1990 .

[29]  Rodolphe Marion,et al.  Measuring trace gases in plumes from hyperspectral remotely sensed data , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Antonio J. Plaza,et al.  A quantitative and comparative analysis of endmember extraction algorithms from hyperspectral data , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[31]  J. Pickands.  Statistical Inference Using Extreme Order Statistics , 1975 .

[32]  Erzsébet Merényi,et al.  Retrieval of apparent surface reflectance from AVIRIS data: A comparison of empirical line, radiative transfer, and spectral mixture methods , 1994 .

[33]  K R Piech.  INTERPRETATION OF SOILS , 1974 .

[34]  D. Cox,et al.  Analysis of Survival Data. , 1985 .

[35]  Louis L. Scharf,et al.  The adaptive coherence estimator: a uniformly most-powerful-invariant adaptive detection statistic , 2005, IEEE Transactions on Signal Processing.

[36]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[37]  E. Ford,et al.  Vegetation's red edge: a possible spectroscopic biosignature of extraterrestrial plants. , 2005, Astrobiology.

[38]  E. M. Winter,et al.  Anomaly detection from hyperspectral imagery , 2002, IEEE Signal Process. Mag..

[39]  B. Gnedenko.  Sur La Distribution Limite Du Terme Maximum D'Une Serie Aleatoire , 1943 .

[40]  Ramazan Gençay,et al.  EVIM: A Software Package for Extreme Value Analysis in MATLAB , 2001 .

[41]  Rama Chellappa,et al.  Average relative radiance transform for subpixel detection , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..

[42]  Rama Chellappa,et al.  A hybrid algorithm for subpixel detection in hyperspectral imagery , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[43]  Glenn Healey,et al.  Models and methods for automated material identification in hyperspectral imagery acquired under unknown illumination and atmospheric conditions , 1999, IEEE Trans. Geosci. Remote. Sens..

[44]  S. J. Sutley,et al.  Ground-truthing AVIRIS mineral mapping at Cuprite, Nevada , 1992 .

[45]  E. Ashton,et al.  Algorithms for the Detection of Su b-Pixel Targets in Multispectral Imagery , 1998 .

[46]  Chein-I Chang,et al.  Estimation of number of spectrally distinct signal sources in hyperspectral imagery , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[47]  James A. Gardner,et al.  Algorithm for de-shadowing spectral imagery , 2002, SPIE Optics + Photonics.

[48]  Heesung Kwon,et al.  Kernel matched subspace detectors for hyperspectral target detection , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[49]  R. Kashyap.  A Bayesian comparison of different classes of dynamic models using empirical data , 1977 .

[50]  John William Strutt,et al.  XV. On the light from the sky, its polarization and colour , 1871 .

[51]  D. Siegmund.  Importance Sampling in the Monte Carlo Study of Sequential Tests , 1976 .

[52]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[53]  Gary A. Shaw,et al.  Hyperspectral subpixel target detection using the linear mixing model , 2001, IEEE Trans. Geosci. Remote. Sens..

[54]  Edmund R. Malinowski,et al.  Theory of error in factor analysis , 1977 .

[55]  D. Cox,et al.  Analysis of Survival Data. , 1986 .

[56]  R. Fisher,et al.  Limiting forms of the frequency distribution of the largest or smallest member of a sample , 1928, Mathematical Proceedings of the Cambridge Philosophical Society.

[57]  R. Kashyap.  Inconsistency of the AIC rule for estimating the order of autoregressive models , 1980 .

[58]  Geoffrey G. Hazel.  Object-level change detection in spectral imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[59]  Chein-I Chang,et al.  Constrained subpixel target detection for remotely sensed imagery , 2000, IEEE Trans. Geosci. Remote. Sens..

[60]  D. Roberts,et al.  Green vegetation, nonphotosynthetic vegetation, and soils in AVIRIS data , 1993 .

[61]  R. Srinivasan,et al.  Simulation of CFAR detection algorithms for arbitrary clutter distributions , 2000 .

[62]  Robert A. Schowengerdt,et al.  Remote sensing, models, and methods for image processing , 1997 .

[63]  John R. Schott,et al.  Remote Sensing: The Image Chain Approach , 1996 .

[64]  George Casella,et al.  Statistical Inference Second Edition , 2007 .

[65]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[66]  Bea Thai,et al.  Invariant subpixel material detection in hyperspectral imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[67]  Xiaoli Yu,et al.  Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution , 1990, IEEE Trans. Acoust. Speech Signal Process..

[68]  S. Tompkins,et al.  Optimization of endmembers for spectral mixture analysis , 1997 .

[69]  Amit Banerjee,et al.  A machine learning approach for finding hyperspectral endmembers , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[70]  S. Johnson,et al.  The constrained signal detector , 2002, IEEE Trans. Geosci. Remote. Sens..

[71]  J. Rissanen.  A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH , 1983 .

[72]  Raymond F. Kokaly,et al.  Surface Reflectance Calibration of Terrestrial Imaging Spectroscopy Data : a Tutorial Using AVIRIS , 2002 .

[73]  J. Settle,et al.  Linear mixing and the estimation of ground cover proportions , 1993 .

[74]  Maurizio Longo,et al.  Comparative performance analysis of some extrapolative estimators of probability tails , 1988, IEEE J. Sel. Areas Commun..

[75]  A. Berk,et al.  FLAASH and MODTRAN4: state-of-the-art atmospheric correction for hyperspectral data , 1999, 1999 IEEE Aerospace Conference. Proceedings (Cat. No.99TH8403).

[76]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.

[77]  Nahum Gat,et al.  Subpixel object detection using hyperspectral imaging for search and rescue operations , 1998, Defense, Security, and Sensing.

[78]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[79]  Jeffrey C. Lagarias,et al.  Convergence Properties of the Nelder-Mead Simplex Method in Low Dimensions , 1998, SIAM J. Optim..

[80]  Qian Du,et al.  Constrained weighted least squares approaches for target detection and classification in hyperspectral imagery , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[81]  Rama Chellappa,et al.  Hybrid Detectors for Subpixel Targets , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[82]  Louis L. Scharf,et al.  The CFAR adaptive subspace detector is a scale-invariant GLRT , 1999, IEEE Trans. Signal Process..

[84]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[85]  Mario Winter,et al.  N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data , 1999, Optics & Photonics.

[86]  John R. Schott,et al.  Use of physics based models in hyperspectral image exploitation , 2002, Applied Imagery Pattern Recognition Workshop, 2002. Proceedings..

[87]  John F. Mustard,et al.  Photometric phase functions of common geologic minerals and applications to quantitative analysis of mineral mixture reflectance spectra , 1989 .

[88]  Thomas Kailath,et al.  Detection of signals by information theoretic criteria , 1985, IEEE Trans. Acoust. Speech Signal Process..

[89]  Richard L. Smith.  Extreme Value Analysis of Environmental Time Series: An Application to Trend Detection in Ground-Level Ozone , 1989 .

[90]  Dimitris G. Manolakis,et al.  Detection algorithms for hyperspectral imaging applications , 2002, IEEE Signal Process. Mag..

[91]  G. Foody,et al.  Sub-pixel land cover composition estimation using a linear mixture model and fuzzy membership functions , 1994 .

[92]  Chein-I Chang,et al.  Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach , 1994, IEEE Trans. Geosci. Remote. Sens..

[93]  李幼升,et al.  Ph , 1989 .

[94]  John F. Mustard,et al.  Spectral unmixing , 2002, IEEE Signal Process. Mag..

[95]  Stephen B. Weinstein,et al.  Theory and application of some classical and generalized asymptotic distributions of extreme values , 1973, IEEE Trans. Inf. Theory.

[96]  Joseph W. Boardman,et al.  Inversion of high spectral resolution data , 1990, Other Conferences.

[97]  D. Landgrebe.  The Evolution of Landsat Data Analysis , 1997 .

[98]  Heesung Kwon,et al.  Kernel adaptive subspace detector for hyperspectral imagery , 2006, IEEE Geoscience and Remote Sensing Letters.

[99]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[100]  L. Haan,et al.  Residual Life Time at Great Age , 1974 .

[101]  Sidney I. Resnick,et al.  Tail estimates motivated by extreme-value theory , 1985 .

[102]  Rama Chellappa,et al.  An Adaptive Threshold Method for Hyperspectral Target Detection , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.