Prediction and Interpretation of Vehicle Trajectories in the Graph Spectral Domain

Marion Neumeier, Sebastian Dorn, Michael Botsch, Wolfgang Utschick

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

1 Zitat (Scopus)

Abstract

This work provides a comprehensive analysis and interpretation of the graph spectral representation of traffic scenarios. Based on a spatiotemporal vehicle interaction graph, an observed traffic scenario can be transformed into the graph spectral domain by means of the multidimensional Graph Fourier Transformation. Since these spectral scenario representations have shown to successfully incorporate the complex and interactive nature of traffic scenarios, the beneficial feature representation is employed for the purpose of predicting vehicle trajectories. This work introduces GFTNNv2, a deep learning network predicting vehicle trajectories in the graph spectral domain. Evaluation of the GFTNNv2 on the publicly available datasets highD and NGSIM shows a performance gain of up to 25 % in comparison to state-of-the-art prediction approaches.

OriginalspracheEnglisch
Titel2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten1172-1179
Seitenumfang8
ISBN (elektronisch)9798350399462
DOIs
PublikationsstatusVeröffentlicht - 2023
Veranstaltung26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023 - Bilbao, Spanien
Dauer: 24 Sept. 202328 Sept. 2023

Publikationsreihe

NameIEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
ISSN (Print)2153-0009
ISSN (elektronisch)2153-0017

Konferenz

Konferenz26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023
Land/GebietSpanien
OrtBilbao
Zeitraum24/09/2328/09/23

Fingerprint

Untersuchen Sie die Forschungsthemen von „Prediction and Interpretation of Vehicle Trajectories in the Graph Spectral Domain“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren