&lt;title&gt;Estimating the degrees of freedom for a common CFAR detector&lt;/title&gt;

Singer, Paul Frank; Sasaki, Doreen M.

doi:10.1117/12.241210

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of Gaussian distributions, the resulting quantile would be + zs, where Za 5 the 1 -quantile of a standard Gaussian distribution. Contrast that to (2). When n = 64 and c = iO, the actual false alarm rate with this substitution approach is 23 times the desired value.…”

Section: Resultsmentioning

confidence: 77%

“…4 One simple situation is the Gaussian white noise situation, where F is a Gaussian distribution with unknown mean and variance, and y and all the v's are independent. Then the choice C = t:i + s(1 + 1/n)'/2ta,ni (2) satisfies (1) exactly, where ti = v, = (n -1)_i 1(v -)2, and tan_i is the critical value for a Student's t-distribution with n -1 degrees of freedom. Then P(y > C) = P( 3" > tan_i) = 8v 1+1/n In this discussion we consider possible methods when • there is dependence among the v's • there is dependence between y and the v's • the distribution is non-Gaussian, with known shape, and…”

Section: Introductionmentioning

confidence: 95%

See 1 more Smart Citation

<title>CFAR detection with non-Gaussian and dependent data</title>

Hesterberg¹

1999

SPIE Proceedings

View full text Add to dashboard Cite

The volume of video and other image data is expanding at a rapid pace with the increasing use of surveillance systems, unmanned vehicles, and other collection systems. The sheer volume of images requires the use of automatic systems to select interesting image features for further analysis. These systems should have a low false alarm rate, e.g. satisfying a pre-determined constant false alarm rate (CFAR). Various filters may be applied to filter out nontarget (background) parts of an image. The output of these filters is noise, plus possible target features. When the noise is Gaussian, CFAR thresholds may be based on t-distributions, with reduced degrees of freedom in the case of correlated noise. For the non-Gaussian case, the use of t distributions is inappropriate, and we suggest alternatives based on parametric families of distributions, with location, scale, and shape parameters. When shape parameters are known the thresholds can be determined using a Monte Carlo technique, using variance reduction techniques to improve the computational efficiency by a factor of 1800. We discuss methods for handling unknown shape parameters.

show abstract

Section: Resultsmentioning

confidence: 77%

Section: Introductionmentioning

confidence: 95%