Title :
A New CFAR Matched Detector for an Autoregressive Model of Noise
Author :
Golikov, V.S. ; Lebedeva, O.M.
Author_Institution :
Dept. of Eng., UNACAR, Mexico City
Abstract :
The constant false alarm rate (CFAR) matched detector (CFAR MD) is the uniformly most-powerful-invariant test and the generalized likelihood ratio test (GLRT) for detecting a target signal in noise whose covariance structure is known but whose level is unknown. The CFAR adaptive subspace detector (CFAR MD) was proposed for detecting a target signal in noise whose covariance structure and level are both unknown. In this paper, we use the theory of GLRTs to adapt the no-adaptive CFAR MDs to unknown noise covariance matrices with autoregressive (AR) structure. In this situation, we proposed a new CFAR NCFMD whose structure does not depend on noise covariance matrix and level and its performance penalty is small
Keywords :
autoregressive processes; covariance matrices; signal detection; CFAR MD; CFAR NCFMD; CFAR adaptive subspace detector; CFAR matched detector; GLRT; autoregressive noise model; constant false alarm rate; covariance matrices; covariance structure; generalized likelihood ratio test; invariant test; target signal detection; Adaptive signal detection; Covariance matrix; Detectors; Noise level; Noise measurement; Signal detection; Signal to noise ratio; Sonar detection; Statistical distributions; Testing; maximum likelihood detection; nonadaptive matched filter; unknown noise covariance matrix;
Conference_Titel :
Electrical and Electronics Engineering, 2006 3rd International Conference on
Conference_Location :
Veracruz
Print_ISBN :
1-4244-0402-9
Electronic_ISBN :
1-4244-0403-7
DOI :
10.1109/ICEEE.2006.251911
