The supervision of underwater areas is essential for the preservation of marine ecosystems. In the Italian context, Professional divers of Environmental Protection Agencies are periodically involved in monitoring activities that are repetitive, dangerous, and expensive. The Ligurian Regional Agency for the Environmental Protection (ARPAL) and the University of Pisa (UNIPI) are collaborating towards the employment of robots and ICT tools to improve the monitoring activities in terms of safety, cost and time effectiveness. This paper reports a strategy to geo-reference underwater visual data using audio for data synchronization. The work refers to a visual dataset acquired by a Smart Dive Scooter (SDS) during a Posidonia Oceanica (Po) monitoring activity in front of the Ligurian Coast. The proposed strategy concerns the synchronization between the audio track recorded by a camera and the transponder pings adopted for the SDS acoustic positioning system. The paper also reports the exploitation of the geo-referenced optical data for the identification of Po meadow over the mission area using a Machine Learning algorithm. The results are very promising and can lead to an accurate geo-referenced identification of Po and the reconstruction of the surveyed area.
Geo-referenced visual data for Posidonia Oceanica coverage using audio for data synchronization
Ruscio F.
;Costanzi R.;Pollini L.;Manzari V.;
2020-01-01
Abstract
The supervision of underwater areas is essential for the preservation of marine ecosystems. In the Italian context, Professional divers of Environmental Protection Agencies are periodically involved in monitoring activities that are repetitive, dangerous, and expensive. The Ligurian Regional Agency for the Environmental Protection (ARPAL) and the University of Pisa (UNIPI) are collaborating towards the employment of robots and ICT tools to improve the monitoring activities in terms of safety, cost and time effectiveness. This paper reports a strategy to geo-reference underwater visual data using audio for data synchronization. The work refers to a visual dataset acquired by a Smart Dive Scooter (SDS) during a Posidonia Oceanica (Po) monitoring activity in front of the Ligurian Coast. The proposed strategy concerns the synchronization between the audio track recorded by a camera and the transponder pings adopted for the SDS acoustic positioning system. The paper also reports the exploitation of the geo-referenced optical data for the identification of Po meadow over the mission area using a Machine Learning algorithm. The results are very promising and can lead to an accurate geo-referenced identification of Po and the reconstruction of the surveyed area.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.