Recursive Estimation Techniques for Detection of Small Objects in Infrared Image Data
Abstract
This paper describes a recursive detection scheme for point targets in infrared (IR) images. Estimation of the background noise is done using a weighted autocorrelation matrix update method and the detection statistic is calculated using a recursive technique. A weighting factor allows the algorithm to have finite memory and deal with nonstationary noise characteristics. The detection statistic is created by using a matched filter for colored noise, using the estimated noise autocorrelation matrix. The relationship between the weighting factor, the nonstationarity of the noise and the probability of detection is described. Some results on one- and two-dimensional infrared images are presented.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1992
- Accession Number
- ADA250942
Entities
People
- J. R. Zeidler
- T. Soni
- W. H. Ku
Organizations
- Naval Command, Control and Ocean Surveillance Center