A Review of Methods for Ship Detection with Electro-Optical Images in Marine Environments

The ocean connects all continents and is an important space for human activities. Ship detection with electro-optical images has shown great potential due to the abundant imaging spectrum and, hence, strongly supports activities in ocean. A suitable can obtain effective complex marine environments, which premise of ship detection. This paper provides overview methods environments. sea–sky backgrounds include traditional deep learning methods. Traditional comprise following steps: preprocessing, line (SSL) detection, region interest (ROI) extraction, identification. use promising detection; however, it requires a large amount labeled data build robust model, its targeted optimization environments not sufficient.