Ship detection based on morphological component analysis of high-frequency surface wave radar images

In this study, high-frequency surface wave radar (HFSWR) is considered for target detection. These systems, commonly used for oceanographic purposes, are of interest in maritime surveillance because of their long range detection capabilities compared with conventional microwave radar. Unfortunately, the received signals are strongly polluted by different noises. In this contribution a target detection method based on morphological component analysis (MCA) is investigated. Basically, MCA is a source separation technique based on multiscale transforms and the sparsity representation. The authors goal is to extract the target signatures from the range-Doppler image and then to take the final decision through a simple rule. This study introduces the issue of ship detection from HFSWR images and gives an overview of the MCA approach. Then, the algorithm used for target detection is depicted. Comparisons with a classical constant false-alarm rate (CFAR) detection method, the so-called greatest of cell averaging-CFAR, are given through receiver operating characteristic curves computed from simulated data.