Efficient and precise calculation of the probability of false alarms for the K-distributed sea clutter and noise is crucial in radar detection system. We propose efficient and optimal importance sampling algorithms, in which two importance sampling estimators are constructed for both the product form and the compound form of the underlying K distribution. Moreover, we prove the existence and uniqueness of the optimal tilting parameters. Detection accuracy and efficiency are analyzed in simulation studies.
|Journal||Communications in Statistics: Simulation and Computation|
|State||Accepted/In press - 1 Jan 2020|
- Constant false alarm rate
- Importance sampling; Simulation