“Multimodal machine learning and signal processing technologies from
multiple heterogeneous information sources for safety applications and
surveillance of critical infrastructures - METIS", General Secretariat for Research and Technology (GSRT) funded project (T1EDK-01169) – www.metis-project.gr
This project aims at developing signal processing, machine learning algorithms and frameworks for semantic information extraction (object detection and recognition, motion tracking, anomaly detection) from multiple heterogeneous information sources (RGB cameras, thermal cameras and various types of radars). It also aims at implementing multimodal information fusion techniques and, ultimately, at building an advanced decision support system for critical infrastructure safety and surveillance applications.
Given the heterogeneity of data flows originating from multiple different sensors, such as RGB cameras, thermal cameras and various types of radars (Long Range Radars, microwave barriers or tripwire microwave sensors), the project will develop pattern recognition and machine learning algorithms appropriate for the different data modalities.