Efficient Size and Heading Angle Estimation of Ships in SAR and ISAR Images

Abstract

For maritime security applications it is advantageous or even required, that additionally to the geographical positions and moving directions the dimensions of the detected ships are available for subsequent classification and recognition purposes. In this paper a fast and robust method for size and heading angle estimation of ships in synthetic aperture radar (SAR) and inverse SAR (ISAR) images is proposed. The novel method leverages the eigenvalue decomposition of the detected ship pixel positions for determining the just mentioned parameters. The effectiveness of the proposed method is assessed against several state-of-the-art methods by using real X-band SAR images acquired with the German TerraSAR-X radar satellite in stripmap mode. The achieved accuracies of the proposed method are better than the ones obtained with the considered state-of-the-art methods and, as a further benefit, the computation time is also significantly shorter.