Deep learning methods for ship traffic surveillance

AI Machine Learning

07 June 13h00-14h00

In view of the increase in illicit maritime activities like piracy, sea robbery, trafficking of narcotics, immigration and illegal fishing, an enhance of accuracy in surveillance is essential in order to ensure safer, cleaner and more secure maritime waterways. Recently, the field of deep learning technology has received considerable attention for integration into the security systems and devices. Consequently, an automated analysis of electro-optical and thermal infrared imagery can decrease the incident response time by processing efficiently large amount of video data and can support the authorities in decision making. In our study, we analyse the practical feasibility of applying various deep learning-based algorithms to generate reports on ship identity, signature and behaviour.

Previous Post Next Post