Band selection with Higher Order Multivariate Cumulants for small target detection in hyperspectral images

In the small target detection problem a pattern to be located is on the order of magnitude less numerous than other patterns present in the dataset. This applies both to the case of supervised detection, where the known template is expected to match in just a few areas and unsupervised anomaly detection, as anomalies are rare by definition. This problem is frequently related to the imaging applications, i.e. detection within the scene acquired by a camera. To maximize available data about the scene, hyperspectral cameras are used; at each pixel, they record spectral data in hundreds of narrow bands. The typical feature of hyperspectral imaging is that characteristic properties of target materials are visible in the small number of bands, where light of certain wavelength interacts with characteristic molecules. A target-independent band selection method based on statistical principles is a versatile tool for solving this problem in different practical applications. Combination of a regular background and a rare standing out anomaly will produce a distortion in the joint distribution of hyperspectral pixels. Higher Order Cumulants Tensors are a natural `window' into this distribution, allowing to measure properties and suggest candidate bands for removal. While there have been attempts at producing band selection algorithms based on the 3 rd cumulant's tensor i.e. the joint skewness, the literature lacks a systematic analysis of how the order of the cumulant tensor used affects effectiveness of band selection in detection applications. In this paper we present an analysis of a general algorithm for band selection based on higher order cumulants. We discuss its usability related to the observed breaking points in performance, depending both on method order and the desired number of bands. Finally we perform experiments and evaluate these methods in a hyperspectral detection scenario.

[1]  Robert L. Brown,et al.  Spectral Angle Mapper classification of fluorescence hyperspectral image for aflatoxin contaminated corn , 2010, 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[2]  Maurice G. Kendall,et al.  The advanced theory of statistics , 1945 .

[3]  Adolfo Martínez Usó,et al.  Clustering-Based Hyperspectral Band Selection Using Information Measures , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Joos Vandewalle,et al.  A Multilinear Singular Value Decomposition , 2000, SIAM J. Matrix Anal. Appl..

[5]  Piotr Gawron,et al.  Efficient Computation of Higher-Order Cumulant Tensors , 2017, SIAM J. Sci. Comput..

[6]  E. L. Hunter,et al.  An assessment of two classification methods for mapping Thames Estuary intertidal habitats using CASI data , 2002 .

[7]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[8]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[9]  George P. Petropoulos,et al.  A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping , 2010, Sensors.

[10]  Nasser M. Nasrabadi,et al.  Hyperspectral Target Detection : An Overview of Current and Future Challenges , 2014, IEEE Signal Processing Magazine.

[11]  Alfred O. Hero,et al.  Joint Bayesian Endmember Extraction and Linear Unmixing for Hyperspectral Imagery , 2009, IEEE Transactions on Signal Processing.

[12]  Heesung Kwon,et al.  Adaptive anomaly detection using subspace separation for hyperspectral imagery , 2003 .

[13]  Yongchao Zhao,et al.  A Fast Volume-Gradient-Based Band Selection Method for Hyperspectral Image , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[14]  S. J. Sutley,et al.  Mapping Advanced Argillic Alteration at Cuprite, Nevada, Using Imaging Spectroscopy , 2014 .

[15]  Qi Wang,et al.  Dual-Clustering-Based Hyperspectral Band Selection by Contextual Analysis , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Chein-I Chang,et al.  Constrained band selection for hyperspectral imagery , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Yongchao Zhao,et al.  Joint Skewness and Its Application in Unsupervised Band Selection for Small Target Detection , 2015, Scientific reports.

[18]  S. Dunagan,et al.  The MARTE VNIR imaging spectrometer experiment: design and analysis. , 2008, Astrobiology.

[19]  Qingquan Li,et al.  A Novel Ranking-Based Clustering Approach for Hyperspectral Band Selection , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Bo Li,et al.  Ship Detection in High-Resolution Optical Imagery Based on Anomaly Detector and Local Shape Feature , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Tze Meng Low,et al.  Exploiting Symmetry in Tensors for High Performance: Multiplication with Symmetric Tensors , 2013, SIAM J. Sci. Comput..

[22]  P. M. van Dijk,et al.  Spectral characterization of ophiolite lithologies in the Troodos Ophiolite complex of Cyprus and its potential in prospecting for massive sulphide deposits , 1997 .

[23]  W. M. Benzel,et al.  USGS Spectral Library Version 7 , 2017 .

[24]  Marcello Picollo,et al.  Reflectance Hyperspectral Imaging for Investigation of Works of Art: Old Master Paintings and Illuminated Manuscripts. , 2016, Accounts of chemical research.

[25]  R. Nelsen An Introduction to Copulas , 1998 .

[26]  Fred A. Kruse,et al.  The Spectral Image Processing System (SIPS) - Interactive visualization and analysis of imaging spectrometer data , 1993 .

[27]  S. J. Sutley,et al.  Imaging spectroscopy: Earth and planetary remote sensing with the USGS Tetracorder and expert systems , 2003 .

[28]  K. Domino Multivariate cumulants in features selection and outlier detection for financial data analysis , 2018, 1804.00541.

[29]  James E. Fowler,et al.  Locality-Preserving Dimensionality Reduction and Classification for Hyperspectral Image Analysis , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Paul Geladi,et al.  NIR spectrometry for counterfeit drug detection - A feasibility study , 2005 .

[31]  E. Lukács CERTAIN ENTIRE CHARACTERISTIC FUNCTIONS , 2005 .

[32]  Marco Diani,et al.  Statistical Analysis of Hyper-Spectral Data: A Non-Gaussian Approach , 2007, EURASIP J. Adv. Signal Process..

[33]  Bruce W. Pengra,et al.  Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm , 2022 .

[34]  J. R. Jensen,et al.  Hyperspectral Remote Sensing of Vegetation , 2008 .

[35]  J. Chanussot,et al.  Hyperspectral Remote Sensing Data Analysis and Future Challenges , 2013, IEEE Geoscience and Remote Sensing Magazine.

[36]  Krzysztof Domino,et al.  Application of hyperspectral imaging and machine learning methods for the detection of gunshot residue patterns. , 2018, Forensic science international.

[37]  Luis O. Jimenez-Rodriguez,et al.  Unsupervised Linear Feature-Extraction Methods and Their Effects in the Classification of High-Dimensional Data , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[38]  D. Sornette,et al.  Multifractal returns and hierarchical portfolio theory , 2000, cond-mat/0008069.

[39]  Boris Hermann,et al.  Robust segmentation of intraretinal layers in the normal human fovea using a novel statistical model based on texture and shape analysis. , 2010, Optics express.

[40]  Kang Sun,et al.  A New Sparsity-Based Band Selection Method for Target Detection of Hyperspectral Image , 2015, IEEE Geoscience and Remote Sensing Letters.

[41]  Qian Du,et al.  Collaborative Representation for Hyperspectral Anomaly Detection , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[42]  Przemysław Głomb,et al.  Automatic pigment identification from hyperspectral data , 2018 .

[43]  Bo Du,et al.  A Sparse Representation-Based Binary Hypothesis Model for Target Detection in Hyperspectral Images , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[44]  Naoto Yokoya,et al.  Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art , 2017, IEEE Geoscience and Remote Sensing Magazine.

[45]  T S Durrani,et al.  Band selection for hyperspectral images using copulas-based mutual information , 2009, 2009 IEEE/SP 15th Workshop on Statistical Signal Processing.