Vehicle tracking with Kalman filter using online situation assessment

摘要

Vehicle tracking is an attractive problem in the field of public transportation with several research projects conducted using Kalman filter (KF) to tackle this. While a driver may act on his own decision, there exist parameters affecting his behavior so called situation assessment such as neighboring drivers, possible obstacles, or alternative routes changing over time. In this paper, utilizing online situation assessment (SA) inside Kalman filter is studied. Motion History Graph is used as online modeling of the history of the vehicle motions and is used to augment the estimation. Experimental results on video sequences from different datasets show an average 25 percent performance improvement when using online SA inside KF. (C) 2020 Elsevier B.V. All rights reserved.