Application of canonical correlation analysis in detection in presence of spatially correlated noise

Wei Guo Chen; James P. Reilly; Kon Max Wong

doi:10.1117/12.49845

1 December 1991 Application of canonical correlation analysis in detection in presence of spatially correlated noise

Wei Guo Chen, James P. Reilly, Kon Max Wong

Proceedings Volume 1566, Advanced Signal Processing Algorithms, Architectures, and Implementations II; (1991) https://doi.org/10.1117/12.49845
Event: San Diego, '91, 1991, San Diego, CA, United States

Abstract

A new approach to the problem of detecting the number of signals in unknown colored noise environments is presented. Based on an assumption that the noise is correlated only over a limited spatial range, the principle of canonical correlation analysis is applied to the outputs of two spatially-separated arrays. The number of signals is determined by testing the significance of the sample canonical correlation coefficients. The new method is shown to work well in both white and unknown colored noise situations and does not require any subjective threshold setting. Instead, a set of threshold values are generated according to a specified or desired false alarm rate. Simulation results are included to illustrate the comparative performance of the proposed canonical correlation technique (CCT), versus the well-known AIC and MDL criteria, in colored noise. It is found that the performance of the AIC and MDL criteria degrade very rapidly as the degree of color in the noise increases. On the other hand, the performance of the CCT method is relatively insensitive with respect to variations in degree of color.

Citation Download Citation

Wei Guo Chen, James P. Reilly, and Kon Max Wong "Application of canonical correlation analysis in detection in presence of spatially correlated noise", Proc. SPIE 1566, Advanced Signal Processing Algorithms, Architectures, and Implementations II, (1 December 1991); https://doi.org/10.1117/12.49845

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available