no code implementations • 7 Dec 2023 • Yongqi Dong, Xingmin Lu, Ruohan Li, Wei Song, Bart van Arem, Haneen Farah
In conclusion, the proposed pipeline, with its incorporation of self-supervised pre-training using MiM and other advanced deep learning techniques, emerges as a robust solution for enhancing the accuracy and efficiency of lane rendering image anomaly detection in digital navigation systems.
no code implementations • 7 Dec 2023 • Lanxin Zhang, Yongqi Dong, Haneen Farah, Arkady Zgonnikov, Bart van Arem
Moreover, previous ML-based approaches predominantly utilize basic vehicle motion features (such as velocity and acceleration) to label and detect abnormal driving behaviors, while this study seeks to introduce Surrogate Safety Measures (SSMs) as the input features for ML models to improve the detection performance.
no code implementations • 29 Oct 2023 • Fanchao Liao, Jaap Vleugel, Gustav Bösehans, Dilum Dissanayake, Neil Thorpe, Margaret Bell, Bart van Arem, Gonçalo Homem de Almeida Correia
To assess their potential to reduce private car use, it is important to investigate to what extent people would switch to eHUBS modes after their introduction.
no code implementations • 20 Jun 2023 • Henan Yuan, Penghui Li, Bart van Arem, Liujiang Kang, Yongqi Dong
Experimental results on various testing scenarios reveal that the TRPO algorithm outperforms DDPG and PPO in terms of safety and efficiency, and PPO performs best in terms of comfort level.
no code implementations • 2 Mar 2022 • Alphonse Vial, Gustaf Hendeby, Winnie Daamen, Bart van Arem, Serge Hoogendoorn
This paper proposes a new method for advanced traffic applications, tracking an unknown and varying number of moving targets (e. g., pedestrians or cyclists) constrained by a road network, using mobile (e. g., vehicles) spatially distributed sensor platforms.
no code implementations • 5 Oct 2021 • Yongqi Dong, Sandeep Patil, Bart van Arem, Haneen Farah
Since lane markings are continuous lines, the lanes that are difficult to be accurately detected in the current single image can potentially be better deduced if information from previous frames is incorporated.