A Rotational Libra R-CNN Method for Ship Detection

Aim:

          To automate the detection of presence of ships and to classify the types of ships available in the given Image.

Synopsis:

         The detection of inshore and offshore ships is an essential task for a large variety of applications in both military and civilian fields. For example, in the civil field, ship detection plays a strong supervisory role in monitoring and managing marine traffics, transportation, fisheries dumping of pollutants and illegal smuggling. The dataset of sea ships images where trained and used to detect the presence of the ships in a given image.

Proposed System:

       In our work, an end-to end method, named as Scene CNN, is proposed to reduce the on shore false alarms. The scene mask extraction network (SMEN), as a network branch for scene segmentation, is innovatively introduced into the detection framework.

       A system is proposed to automate the detection of presence of ships in the given image using Machine Learning and Deep Learning Algorithms. We are proposing along with ship detection, a ship classification based on the type and category of the ships. The proposed system will not only detect a ship but also categorize as war ship, container ship etc.