Marine life observation using classification algorithms on ocean surface photographs

The growth of marine renewable energy and marine protected areas in France leads to an increased need for animal population knowledge at sea. Offshore energy generator projects (wind turbines for example) must obey these regulations and show their harmlessness to the environment, particularly to the wildlife and to protected species, which are vulnerable and threatened. The work presented in this paper is part of a project whose goal is to propose a system of sea surface survey by plane, using numerical HD photography. Data will be recorded in daylight with a flight plan allowing to cover all of the sea surface to be studied. This paper introduces a solution to use these images to detect and classify the objects present on the sea surface, near this surface or in the air column under the plane: birds, marine mammals, turtles and sharks (near the surface), ships, other mankind objects (waste).