Near Real Time (NRT) Suspect Vessel Identification (SVI) system
Paulo Miguel Nunes do Carmo(1)
(1) Edisoft, SA, Apartado 382 Monte Caparica, 2826-801 Caparica, Portugal
The intrinsic characteristics of the Synthetic Aperture Radar (SAR), like the possibility to acquire images in all-weather, day/night conditions, together with its range of possible resolutions and covered areas,
have placed it as an important data source for ocean monitoring. This paper discusses an automated Near Real Time (NRT) Suspect Vessel Identification (SVI) system, which uses, among others, imagery from
SAR satellites. This system is mainly constituted by two components. The first component is an automated SAR multi mission detection and classification software which is able to detect and classify
vessels within a SAR image. This component is capable of processing multi sensor SAR images like ERS-2 and ENVISAT and in the future COSMO SkyMed, TerraSAR-X and RADARSAT. The second component is a suspect vessel identification software, which correlates the SAR detection and
classification data with other non EO data like AIS/VTS/VMS (and in the future LRIT) to find suspect vessels. This component then applies a set of criteria on the data, to identify the detected vessels that can
be considered as suspects and so should be subject to further investigation by the adequate maritime authorities.
To finalise, it will be presented some of the performed verification and validation activities, the foreseen evolution of the system and the conclusions.
Keywords: ESA European
Space Agency - Agence spatiale europeenne,
observation de la terre, earth observation,
satellite remote sensing,
teledetection, geophysique, altimetrie, radar,
chimique atmospherique, geophysics, altimetry, radar,