This project aims at analysing the traffic flow of open roads in real time by a sensor fusion of radar data with video feeds. Radar gives an accurate position and velocity of vehicles making computer vision methods more robust in computing their spatial extent and classification from video streams. In this way the huge amount of raw data is reduced to semantically relevant information, which is highly memory efficient, anonymous and sufficient to reconstruct traffic flow over long time periods. Another important goal is a sophisticated 3D visualization of the reconstructed traffic flow providing interactive tools for visual analysis. Information obtained in this way will significantly contribute in adopting measures to increase traffic safety.
In this area, we concentrate on algorithms that synthesize images to depict 3D models or scenes, often by simulating or approximating the physics of light.
In this area, we focus on researching methods and algorithms that facilitate creation, representation, analysis and processing of 3D models.