Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

An RNN-Based IMM Filter Surrogate

: Becker, Stefan; Hug, Ronny; Hübner, Wolfgang; Arens, Michael


Felsberg, Michael (Hrsg.) ; International Association for Pattern Recognition -IAPR-:
Image Analysis. 21st Scandinavian Conference, SCIA 2019. Proceedings : Norrköping, Sweden, June 11–13, 2019
Cham: Springer Nature, 2019 (Lecture Notes in Computer Science 11482)
ISBN: 978-3-030-20204-0 (Print)
ISBN: 978-3-030-20205-7
Scandinavian Conference on Image Analysis (SCIA) <21, 2019, Norrköping>
Conference Paper
Fraunhofer IOSB ()
trajectory forecasting; path prediction; IMM filter; multiple model filter

The problem of varying dynamics of tracked objects, such as pedestrians, is traditionally tackled with approaches like the Interacting Multiple Model (IMM) filter using a Bayesian formulation. By following the current trend towards using deep neural networks, in this paper an RNN-based IMM filter surrogate is presented. Similar to an IMM filter solution, the presented RNN-based model assigns a probability value to a performed dynamic and, based on them, puts out a multi-modal distribution over future pedestrian trajectories. The evaluation is done on synthetic data, reflecting prototypical pedestrian maneuvers.