PROJECT TITLE :

Ship Classification Based on Superstructure Scattering Features in SAR Images

ABSTRACT:

This letter presents a unique technique for ship classification that uses artificial-aperture-radar pictures to differentiate ships based mostly on superstructure scattering features. The ratio of dimensions, that combines the two-D and 3-D properties of scattering, is explored as an effective and credible means to explain the scattering features of ships. The proposed technique consists of 3 main stages: 1) ship isolation from the ocean; a pair of) parametric vector estimation; and 3) categorization using a support vector machine (SVM) classifier. To depict ship options a lot of accurately and cut back feature redundancy, we have a tendency to propose employing peak extraction to divide a ship into bow, middle, and stern rather than into three equal components. The classification methodology is tested with RadarSat-two pictures, and ground-truth information is equipped by an automatic identification system. The experimental results show that the proposed technique can achieve satisfactory ship-classification performance compared with existing strategies, with an overall accuracy exceeding 80%.