Chi-square statistic for noise objects tracking in Track-Before-Detect systems
2012
scientific article
english
- Track-Before-Detect system
- TBD
- Chi-square statistic
- tracking system
EN Tracking of the noise signal in noise measurements needs special techniques. The difference between object and background noise is defined, using the noise parameter estimators. The proposed technique is based on the model of the noise and the Gaussian noise is assumed. The window based approach is used for input signal preprocessing. The chi-square statistic for estimation of the local chi-square value by the comparison of the assumed model and local distributions is used. Chi-square values are processed using Spatio-Temporal Track-Before-Detect Algorithm for tracking of the dynamic of the object and improved signal denoising. Dumped Information Update formula is proposed for considered TBD algorithm. A few examples are shown for different objects that show possibilities of the proposed solution.
177 - 184