Kernel Anomalous Change Detection for Remote Sensing Imagery

Anomalous change detection (ACD) is an important problem in remote sensing image processing. Detecting not only pervasive but also anomalous or extreme changes has many applications for which methodologies are available. This paper introduces a nonlinear extension of a full family of anomalous change detectors. In particular, we focus on algorithms that utilize Gaussian and elliptically contoured (EC) distribution and extend them to their nonlinear counterparts based on the theory of reproducing kernels’ Hilbert space. We illustrate the performance of the kernel methods introduced in both pervasive and ACD problems with real and simulated changes in multispectral and hyperspectral imagery with different resolutions (AVIRIS, Sentinel-2, WorldView-2, and Quickbird). A wide range of situations is studied in real examples, including droughts, wildfires, and urbanization. Excellent performance in terms of detection accuracy compared to linear formulations is achieved, resulting in improved detection accuracy and reduced false-alarm rates. Results also reveal that the EC assumption may be still valid in Hilbert spaces. We provide an implementation of the algorithms as well as a database of natural anomalous changes in real scenarios http://isp.uv.es/kacd.html.

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

[2]  William J. Emery,et al.  Automatic damage detection Using pulse-coupled neural networks For the 2009 Italian earthquake , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[3]  Jun Chen,et al.  Change Vector Analysis in Posterior Probability Space: A New Method for Land Cover Change Detection , 2011, IEEE Geoscience and Remote Sensing Letters.

[4]  William J. Emery,et al.  Pulse Coupled Neural Networks for detecting urban areas changes at very high resolutions , 2009, 2009 Joint Urban Remote Sensing Event.

[5]  Chiman Kwan,et al.  A Novel Cluster Kernel RX Algorithm for Anomaly and Change Detection Using Hyperspectral Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Qi Wang,et al.  Fast Hyperspectral Anomaly Detection via High-Order 2-D Crossing Filter , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Luis Gómez-Chova,et al.  Explicit signal to noise ratio in reproducing kernel Hilbert spaces , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[8]  Michael E. Hodgson,et al.  Optimizing the binary discriminant function in change detection applications , 2008 .

[9]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[10]  Kaare Brandt Petersen,et al.  Kernel Multivariate Analysis Framework for Supervised Subspace Learning: A Tutorial on Linear and Kernel Multivariate Methods , 2013, IEEE Signal Processing Magazine.

[11]  Eero P. Simoncelli,et al.  Nonlinear Extraction of Independent Components of Natural Images Using Radial Gaussianization , 2009, Neural Computation.

[12]  W. Malila.  Change Vector Analysis: An Approach for Detecting Forest Changes with Landsat , 1980 .

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

[14]  Francesca Bovolo,et al.  A Context-Sensitive Technique for Unsupervised Change Detection Based on Hopfield-Type Neural Networks , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2004 .

[16]  Francesca Bovolo,et al.  A Split-Based Approach to Unsupervised Change Detection in Large-Size Multitemporal Images: Application to Tsunami-Damage Assessment , 2007, IEEE Transactions on Geoscience and Remote Sensing.

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

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

[19]  Gary A. Shaw,et al.  Hyperspectral Image Processing for Automatic Target Detection Applications , 2003 .

[20]  Francesca Bovolo.  A Multilevel Parcel-Based Approach to Change Detection in Very High Resolution Multitemporal Images , 2009, IEEE Geosci. Remote. Sens. Lett..

[21]  Gustavo Camps-Valls,et al.  Unsupervised change detection by kernel clustering , 2010, Remote Sensing.

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

[23]  Maoguo Gong,et al.  A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[24]  José Luis Rojo-Álvarez,et al.  Digital Signal Processing with Kernel Methods , 2018 .

[25]  Raúl Santos-Rodríguez,et al.  Signal-to-noise ratio in reproducing kernel Hilbert spaces , 2018, Pattern Recognit. Lett..

[26]  Francesca Bovolo,et al.  Analysis and Adaptive Estimation of the Registration Noise Distribution in Multitemporal VHR Images , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Norman R. Draper,et al.  Residuals and Their Variance Patterns , 1972 .

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

[29]  James Theiler,et al.  Local Coregistration Adjustment for Anomalous Change Detection , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Pol Coppin,et al.  Review ArticleDigital change detection methods in ecosystem monitoring: a review , 2004 .

[31]  Allan Aasbjerg Nielsen,et al.  Kernel Maximum Autocorrelation Factor and Minimum Noise Fraction Transformations , 2011, IEEE Transactions on Image Processing.

[32]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[33]  Turgay Çelik,et al.  Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means Clustering , 2009, IEEE Geoscience and Remote Sensing Letters.

[34]  M. Aizerman,et al.  Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning , 1964 .

[35]  Gustavo Camps-Valls,et al.  Kernel spectral angle mapper , 2016 .

[36]  Gustavo Camps-Valls,et al.  Unsupervised Change Detection With Kernels , 2012, IEEE Geoscience and Remote Sensing Letters.

[37]  S. G. Beaven,et al.  Comparison of Gaussian mixture and linear mixture models for classification of hyperspectral data , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[38]  Zhengyou Zhang,et al.  Improving multiview face detection with multi-task deep convolutional neural networks , 2014, IEEE Winter Conference on Applications of Computer Vision.

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

[40]  Turgay Çelik,et al.  Multiscale Change Detection in Multitemporal Satellite Images , 2009, IEEE Geoscience and Remote Sensing Letters.

[41]  Mark J. Carlotto,et al.  A cluster-based approach for detecting man-made objects and changes in imagery , 2005, IEEE Transactions on Geoscience and Remote Sensing.

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

[43]  R. Dennis Cook,et al.  Detection of Influential Observation in Linear Regression , 2000, Technometrics.

[44]  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.

[45]  D. Lu,et al.  Change detection techniques , 2004 .

[46]  Dean A. Scribner,et al.  Object detection by using "whitening/dewhitening" to transform target signatures in multitemporal hyperspectral and multispectral imagery , 2003, IEEE Trans. Geosci. Remote. Sens..

[47]  Chein-I Chang,et al.  Anomaly detection and classification for hyperspectral imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[48]  Jon Atli Benediktsson,et al.  An Unsupervised Technique Based on Morphological Filters for Change Detection in Very High Resolution Images , 2008, IEEE Geoscience and Remote Sensing Letters.

[49]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[50]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[51]  Xiaoli Yu,et al.  Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach , 1997, IEEE Trans. Image Process..

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

[53]  Xiaogang Wang,et al.  DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[54]  Heesung Kwon,et al.  Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[55]  Yuan Yuan,et al.  Hyperspectral Anomaly Detection by Graph Pixel Selection , 2016, IEEE Transactions on Cybernetics.

[56]  David W. Scott,et al.  Scott's rule , 2010 .

[57]  Ashbindu Singh,et al.  Review Article Digital change detection techniques using remotely-sensed data , 1989 .

[58]  James Theiler,et al.  Detection of ephemeral changes in sequences of images , 2008, 2008 37th IEEE Applied Imagery Pattern Recognition Workshop.

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

[60]  G. Simons,et al.  On the theory of elliptically contoured distributions , 1981 .

[61]  Lorenzo Bruzzone,et al.  Kernel methods for remote sensing data analysis , 2009 .

[62]  Zheng Tian,et al.  Registration Using Robust Kernel Principal Component for Object-Based Change Detection , 2010, IEEE Geoscience and Remote Sensing Letters.

[63]  Bo Du,et al.  Kernel Slow Feature Analysis for Scene Change Detection , 2017, IEEE Transactions on Geoscience and Remote Sensing.