Towards Posidonia Meadows Detection, Mapping and Automatic recognition using Unmanned Marine Vehicles

This paper reports the development of a new methodology for automatic detection and mapping of underwater vegetation by means of highly autonomous marine robotic platforms. In particular, the work describes the exploitation of a Remotely Operated Vehicle (ROV), equipped with a multi-parametric sensors package, for the exploration and characterization of sea-bottoms interested by the presence of the Posidonia oceanica seagrass, which represents a valuable indicator of the environmental health. The proposed methodology relies on the systematic exploration of the sea-bottom by means of the ROV acquiring acoustic data and video imagery of the seabed, in order to reconstruct a 2.5D model of the environment (i.e. an elevation map of the sea-bottom). The data collection is achieved by the employment of a single beam echosounder for seabed range measurements and a down-looking underwater camera. Furthermore, an acoustic data procedural analysis is developed to automatically detect the Posidonia presence, so that in future works it will be possible to operate also in low-visibility conditions. Data acquisition was carried out over different seafloor types in coastal area near Biograd Na Moru (Croatia) and the results are reported in the paper.