SAR Ship Detection Using Image Histograms and Machine Learning Approach

Detection of objects through remote sensing is a current research area. Ship detection in SAR images is a very intense research area today. Convenience is provided to those concerned in applications such as military surveillance and tracking of commercial ships. In this study, ship images were classified using the Hessian matrix and HOG algorithm. Using the eigenvalues of the Hessian matrix, the angle and orientation information of the HOG method was calculated. Thus, distinctive pixel characteristics were coded. The proposed method has achieved successful results in experimental studies.