Detection of radar targets embedded in sea ice and sea clutter using fractals, wavelets, and neural networks

A novel algorithm associated with fractal pre-processors, wavelet feature e xtractors and unsupervised neural classifiers is proposed for detecting rad ar targets embedded in sea ice and sea clutter. Utilizing the advantages of fractals, wavelets and neural networks, the algorithm is suitable for real -time and automatic applications. Fractal preprocessor can increase 10 dB s ignal-to-clutter ratios (S/C) for radar images by using fractal error. Frac tal error will make easy to detect radar targets embedded in high clutter e nvironments. Wavelet feature extractors with a high speed computing archite cture, can extract enough information for classifying radar targets and clu tter, and improve signal-to-clutter ratios. Wavelet feature extractors can also provide flexible combinations for feature vectors at different clutter environments. The unsupervised neural classifier has a parallel operation architecture easily applied to hardware, and a low computational load algor ithm without manual interventions during learning stage. We modified the un supervised competitive learning algorithm to be applicable for detecting sm all radar targets by introducing an asymmetry neighborhood factor. The asym metry neighborhood factor can provide a protective learning to prevent inte rference from clutter and improve the learning effects of radar targets. Th e small radar targets in Millimeter wave (MMW) and X-band radar images have been successfully discriminated by our proposed algorithm. The effective, efficient, high noise immunity characteristics for our proposed algorithm h ave been demonstrated to be suitable for automatic and real time applicatio ns.