DETECTING ANISOTROPIC SCATTERING WITH HIDDEN MARKOV-MODELS

The authors propose that hidden models (HMMs) and multiaperture synthe tic aperture radar (MASAR) imaging can be used to construct automatic target detection algorithms. Their preliminary studies show that HMM M ASAR detection: effectively exploits anisotropic scattering difference s between target and multiple clutter classes is computationally effic ient; call be used with either single polarisation or multipolarisatio n SAR imagery; and can be used with either coherent or noncoherent sub apertures. Further, the results indicate that the accuracy of HMM MASA R detection is comparable to other techniques while requiring orders o f magnitude less computation. These results suggest that the HMM MASAR detection technique could be effectively deployed in fielded automati c target recognition systems.