ThreatDetect: An Autonomous Platform to secure Marine Infrastructures

By: Casari P., Lampe L., Martinez S., Diamant R.
Published in: NATO Science for Peace and Security Series B: Physics and Biophysics
SDGs : SDG 14  |  Units: Marine Sciences  | Time: 2020 |  Link
Description: The NATO SPS multi-year project ThreatDetect investigates an autonomous platform to secure marine infrastructures by rel iably detecting divers and mines in real time. Our system combines acoustic remote detection with verification using pattern recognition on underwater imagery. For diver detection, we rely on active acoustics from a single transceiver, and analyze the acoustic reflections to detect and localize a target that fits the pattern of a diver. For mine detection, we segment sonar images from an autonomous underwater vehicle (AUV) to differentiate between background, highlight, and shadow. In case of detection, we steer the AUV’s trajectory so as to closely observe the target, and transmit segmented sonar images to a surface station via underwater acoustic communications. At the time of writing, the project is performing final technology tuning and integrated sea experiments. © 2020, Springer Nature B.V.