Canonical Correlation Analysis for Coherent Change Detection in Synthetic Aperture Sonar Imagery

The application of coherent change detection has enabled the synthetic aperture radar community to identify manmade changes in repeat-pass imagery not detectable in magnitude only images. In a similar manner, CCD may allow synthetic aperture sonar community to identify man-made changes on the seafloor. We propose a coherent change detection scheme using canonical correlation analysis to determine the linear dependence between the canonical coordinates of the input channels, which are represented by baseline and repeat survey pass of the synthetic aperture sonar. We demonstrate the versatility of this method with application to a synthetic aperture sonar imagery data set with identical trajectory and modest scene change.

[1]  R. Stolt.  MIGRATION BY FOURIER TRANSFORM , 1978 .

[2]  Mahmood R. Azimi-Sadjadi,et al.  Two-channel constrained least squares problems: solutions using power methods and connections with canonical coordinates , 2005, IEEE Transactions on Signal Processing.

[3]  M.R. Azimi-Sadjadi,et al.  Buried underwater target classification using frequency subband coherence analysis , 2008, OCEANS 2008.

[4]  M.R. Azimi-Sadjadi,et al.  Canonical Coordinates for Detection and Classification of Underwater Objects From Sonar Imagery , 2007, OCEANS 2007 - Europe.

[5]  Mahmood R. Azimi-Sadjdadi,et al.  Target detection from dual disparate sonar platforms using canonical correlations , 2008, SPIE Defense + Commercial Sensing.

[6]  Mahmood R. Azimi-Sadjadi,et al.  Coherent-based method for detection of underwater objects from sonar imagery , 2007, SPIE Defense + Commercial Sensing.

[7]  D. G. Corr.  Coherent change detection for urban development monitoring , 1997 .

[8]  Richard J. Rikoski,et al.  Holographic navigation , 2008, 2008 IEEE International Conference on Robotics and Automation.

[9]  D. G. Corr,et al.  Coherent change detection of vehicle movements , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[10]  N.A. Rimski-Korsakov,et al.  Simple digital system for side scan sonar data imaging , 1994, Proceedings of OCEANS'94.

[11]  James F. Baldwin,et al.  Automatic change detection in spaceborne SAR imagery , 1996, Defense, Security, and Sensing.

[12]  Morton J. Canty,et al.  Unsupervised change detection techniques using multispectral satellite images , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[13]  Gene H. Golub,et al.  Matrix computations (3rd ed.) , 1996 .

[14]  H. Hotelling.  Relations Between Two Sets of Variates , 1936 .

[15]  John K. Thomas,et al.  Canonical Coordinates are the Right Coordinates for Low-Rank Gauss–Gauss Detection and Estimation , 2006, IEEE Transactions on Signal Processing.

[16]  Louis L. Scharf,et al.  Canonical coordinates and the geometry of inference, rate, and capacity , 2000, IEEE Trans. Signal Process..

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

[18]  W. H. Key,et al.  Side scan sonar technology , 2000, OCEANS 2000 MTS/IEEE Conference and Exhibition. Conference Proceedings (Cat. No.00CH37158).

[19]  Richard Bamler,et al.  A comparison of range-Doppler and wavenumber domain SAR focusing algorithms , 1992, IEEE Trans. Geosci. Remote. Sens..