Machine Learning Based Ship Detection Technique

Abstract

Ship Detection has a wide range of applications in the commercial/military area, and maritime security is an increasing and important need for every country across the globe. It helps to prevent and investigate different unlawful actions as well as environmental hazards present at sea. This paper presents a novel Ship Detection technique from high-resolution satellite images with the help of Convolutional Neural Networks(CNN). The proposed system uses Machine Learning techniques for image processing. CNN has been used extensively to get good accuracy and has been most successful in the past. The described approach provides reasonable performance and therefore is potentially suitable for near-real-time (NRT) applications.