Bayesian track-to-graph association for maritime traffic monitoring
We present a hypothesis test to associate ship track measurements to an edge of a given graph that statistically models common traffic routes in a given area of interest. The association algorithm is based on the hypothesis that ship velocities are modeled by mean-reverting stochastic processes. Prior knowledge about the traffic is provided by the graph in form of probability density functions of the mean-reverting kinematic parameters for each node and edge of the graph, which are exploited in the formalization of the association algorithm. Tests on real Automatic Identification System (AIS) data show a qualitatively good association performance. Future developments of this work include the development of specific quantitative metrics to assess the association performance.
SourceIn: 2018 26th European Signal Processing Conference (EUSIPCO), Rome, Italy, 3-7 September 2018, pp. 1042-1046, doi: 10.23919/EUSIPCO.2018.8553443