Vehicle tracking and analysis within a city

Sensor-oriented vehicle tracking and analysis within a city (VTAC) plays an important role in transportation control, public facility management and national security. This project is dedicated to the development of a generic VTAC framework, which employs temporal and spatial dependent partial differential equations (PDE) to formulate the expected traffic flow, through which movement of the observed vehicles may be measured and analysis. The boundary conditions and parameters for the traffic flow are derived from the statistical analysis about historical transportation data; the physics domain is derived from the geographic information system. Using the artificial video data generated by Blender as benchmark data, the VTAC framework is validated by measuring and identifying those anomalous vehicles appeared in the video.