Underwater photogrammetry, if correctly applied, can provide very high resolution and very
accurate models for mapping and monitoring the restoration actions of degraded seafloor
through the reforestation of seagrasses.
Object-Based Image Analysis (OBIA) image analysis performs advanced classification capable
of incorporating spectral data, color, texture, shape and other contextual information to identify
thematic classes in images derived from optical and acoustic data. In particular, the OBIA
classification uses a multi-resolution segmentation of the image to identify homogeneous objects
(note: the term "object" in this case means a contiguous group of spatial data, such as pixels in a
bathymetric grid).
The segmentation process is based on predefined parameters, such as compactness, shape and
scale, derived from real knowledge of the characteristics to be identified and classified.
S Y S D E C O I T A L I A
P A G I N A | 0 1
In this study, photogrammetric surveys
were conducted on sites reforested
with Posidonia oceanica located in five
different areas, four of which in Italy
(central and southern Tyrrhenian Sea
and Strait of Sicily) and one in France
(central Tyrrhenian Sea). Specifically,
the results of the analysis of the
processing of two orthomosaics of the
Capo Feto site (Sicily) are reported
Orthomosaics were classified using an OBIA approach with Trimble's eCognition suite and
applying a supervised k-NN classification algorithm.