Extended Kalman Filter for Large Scale VesselsTrajectory Tracking in Distributed StreamProcessing Systems

Katarzyna Juraszek, Nidhi Saini, Marcela Charfuelan Oliva, Holmer Hemsen, Volker Mark

In: 4th Workshop on Advanced Analytics and Learning on Temporal Data. ECML/PKDD - European Conference of Maschine Learning (AALTD-2019) September 16-20 Würzburg Germany ECML PKDD 2019.


The growing number of vehicle data being constantly reported by a variety of remote sensors, such as Automatic IdentificationSystems (AIS), requires new data analytics methods that can operateat high data rates and are highly scalable. Based on a real-life data set from maritime transport, we propose a large scale vessels trajectory tracking application implemented in the distributed stream processingsystem Apache Flink. By implementing a state-space model (SSM) - the Extended Kalman Filter (EKF) - we firstly demonstrate that an implementation of SSMs is feasible in modern distributed data flow systems and secondly we show that we can reach a high performance by leveraging the inherent parallelization of the distributed system. In our experiments we show that the distributed tracking system is able to handle a throughput of several hundred vessels per ms. Moreover, we show that the latency to predict the position of a vessel is well below 500 ms on average, allowing for real-time applications.


Weitere Links

AALTD_19_Juraszek.pdf (pdf, 2 MB )

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz