Visual characterization and automatic detection of posidonia oceanica for meadows mapping using an auv

Abstract

Detection and mapping of Posidonia Oceanica (P.O.) meadows in the Mediterranean sea is crucial to preserve the endemic ecosystems and to underscore the negative impact of many anthropogenic activities. Furthermore, navigating Autonomous Underwater Vehicles (AUV) in marine environments where the ground is densely colonized with P.O. is nowadays a challenging task, since this sea-grass generates dynamic and extremely textured areas, difficult to match in consecutive or loop-closing images. This paper presents two important contributions: a) a complete assessment to characterize areas of P.O. with visual features, in order to obtain visual localization data as accurate as possible; b) the automatic detection of P.O. in video sequences grabbed from the AUV Sparus II in coastal areas; the images containing the detected sea-grass will be used later to build visual mosaics showing the real extension and form of the P.O. meadow.