Overlapping image segmentation for context-dependent anomaly detection

The challenge of finding small targets in big images lies in the characterization of the background clutter. The more homogeneous the background, the more distinguishable a typical target will be from its background. One way to homogenize the background is to segment the image into distinct regions, each of which is individually homogeneous, and then to treat each region separately. In this paper we will report on experiments in which the target is unspecified (it is an anomaly), and various segmentation strategies are employed, including an adaptive hierarchical tree-based scheme. We find that segmentations that employ overlap achieve better performance in the low false alarm rate regime.

[1]  James Theiler,et al.  Elliptically Contoured Distributions for Anomalous Change Detection in Hyperspectral Imagery , 2010, IEEE Geoscience and Remote Sensing Letters.

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

[3]  S. Süsstrunk,et al.  SLIC Superpixels ? , 2010 .

[5]  Qian Du,et al.  Efficient anomaly detection and discrimination for hyperspectral imagery , 2002, SPIE Defense + Commercial Sensing.

[6]  James Theiler,et al.  Contiguity-enhanced k-means clustering algorithm for unsupervised multispectral image segmentation , 1997, Optics & Photonics.

[7]  Knut Conradsen,et al.  Multivariate Alteration Detection (MAD) and MAF Postprocessing in Multispectral, Bitemporal Image Data: New Approaches to Change Detection Studies , 1998 .

[8]  Alan A. Stocker,et al.  Advanced algorithms for autonomous hyperspectral change detection , 2004, 33rd Applied Imagery Pattern Recognition Workshop (AIPR'04).

[9]  Neal R. Harvey,et al.  Simulation framework for spatio-spectral anomalous change detection , 2009, Defense + Commercial Sensing.

[10]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[11]  Amit Banerjee,et al.  A support vector method for anomaly detection in hyperspectral imagery , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[12]  William F. Basener.  Clutter and anomaly removal for enhanced target detection , 2010, Defense + Commercial Sensing.

[13]  Alan D. Stocker,et al.  Automated hyperspectral target detection and change detection from an airborne platform: Progress and challenges , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[14]  S Matteoli,et al.  A tutorial overview of anomaly detection in hyperspectral images , 2010, IEEE Aerospace and Electronic Systems Magazine.

[15]  Mehrdad Soumekh,et al.  Hyperspectral anomaly detection within the signal subspace , 2006, IEEE Geoscience and Remote Sensing Letters.

[16]  Allan Aasbjerg Nielsen,et al.  The Regularized Iteratively Reweighted MAD Method for Change Detection in Multi- and Hyperspectral Data , 2007, IEEE Transactions on Image Processing.

[17]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[18]  James Theiler,et al.  Sensitivity of anomalous change detection to small misregistration errors , 2008, SPIE Defense + Commercial Sensing.

[19]  J. Theiler,et al.  Subpixel Anomalous Change Detection in Remote Sensing Imagery , 2008, 2008 IEEE Southwest Symposium on Image Analysis and Interpretation.

[20]  M. Bernhardt,et al.  New models for hyperspectral anomaly detection and un-mixing , 2005 .

[21]  N. Nasrabadi,et al.  Kernel RX : A new nonlinear anomaly detector , 2005 .

[22]  E. Forgy.  Cluster analysis of multivariate data : efficiency versus interpretability of classifications , 1965 .

[23]  A. Schaum,et al.  Linear chromodynamics models for hyperspectral target detection , 2003, 2003 IEEE Aerospace Conference Proceedings (Cat. No.03TH8652).

[24]  Daniel Llamocca,et al.  Using support vector machines for anomalous change detection , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[25]  Don R. Hush,et al.  A Classification Framework for Anomaly Detection , 2005, J. Mach. Learn. Res..

[26]  James Theiler,et al.  Effect of signal contamination in matched-filter detection of the signal on a cluttered background , 2006, IEEE Geoscience and Remote Sensing Letters.

[27]  Alan P. Schaum.  Autonomous Hyperspectral Target Detection with Quasi-Stationarity Violation at Background Boundaries , 2006, 35th IEEE Applied Imagery and Pattern Recognition Workshop (AIPR'06).

[28]  A. Schaum.  A remedy for nonstationarity in background transition regions for real time hyperspectral detection , 2006, 2006 IEEE Aerospace Conference.

[29]  James Theiler,et al.  Resampling approach for anomaly detection in multispectral images , 2003, SPIE Defense + Commercial Sensing.

[30]  Lorenzo Bruzzone,et al.  Automatic analysis of the difference image for unsupervised change detection , 2000, IEEE Trans. Geosci. Remote. Sens..

[31]  James Theiler,et al.  Resampling approach for anomalous change detection , 2007, SPIE Defense + Commercial Sensing.

[32]  Russell C. Hardie,et al.  Hyperspectral Change Detection in the Presenceof Diurnal and Seasonal Variations , 2008, IEEE Transactions on Geoscience and Remote Sensing.

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

[34]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[35]  Robert P. W. Duin,et al.  Uniform Object Generation for Optimizing One-class Classifiers , 2002, J. Mach. Learn. Res..

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

[37]  Sean Murphy,et al.  A new approach to anomaly detection in hyperspectral images , 2003, SPIE Defense + Commercial Sensing.

[38]  Joseph Meola,et al.  Airborne hyperspectral detection of small changes. , 2008, Applied optics.

[39]  A. P. Schaum,et al.  Hyperspectral anomaly detection beyond RX , 2007, SPIE Defense + Commercial Sensing.

[40]  Michael T. Eismann,et al.  Image misregistration effects on hyperspectral change detection , 2008, SPIE Defense + Commercial Sensing.

[41]  Ashutosh Kumar Singh,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2010 .

[42]  Steven M. Adler-Golden.  Improved hyperspectral anomaly detection in heavy-tailed backgrounds , 2009, 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[43]  Stanley R. Rotman,et al.  Anomaly detection in non-stationary backgrounds , 2010, 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[44]  James Theiler,et al.  Proposed Framework for Anomalous Change Detection , 2006 .

[45]  James Theiler,et al.  A structural framework for anomalous change detection and characterization , 2009, Defense + Commercial Sensing.

[46]  Don R. Hush,et al.  Statistics for characterizing data on the periphery , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[47]  Chris Clifton.  Change Detection in Overhead Imagery Using Neural Networks , 2004, Applied Intelligence.

[48]  James Theiler,et al.  Quantitative comparison of quadratic covariance-based anomalous change detectors. , 2008, Applied optics.

[49]  Lakshman Prasad,et al.  Hierarchical image segmentation by polygon grouping , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[50]  K.W. Bauer,et al.  Finding Hyperspectral Anomalies Using Multivariate Outlier Detection , 2007, 2007 IEEE Aerospace Conference.

[51]  Shai Ben-David,et al.  Learning Distributions by Their Density Levels: A Paradigm for Learning without a Teacher , 1997, J. Comput. Syst. Sci..

[52]  Lakshman Prasad,et al.  Vectorized Image Segmentation via Trixel Agglomeration , 2005, GbRPR.