Citation

Zhou M, Hou X, Nie L. Transp. Res. F Traffic Psychol. Behav. 2019; 65: 760-771.

Copyright

(Copyright © 2019, Elsevier Publishing)

DOI

10.1016/j.trf.2018.07.012

PMID

unavailable

Abstract

It is an economic and safe way to train novice drivers by means of a simulator as a critical infrastructure where road scenes shall be modeled asapartofvirtually to replace the actual driving conditions but the real-world driving and road situations are conceptualized programmatically based on experiences and knowledge of those designers as far as those existing approaches are concerned. Unlike most previous work, our approach focused on representation of the real-world highway driving circumstances in our driving simulator based on virtual driving experiences; thus, a 3D digital highway model was put forward by utilizing heterogeneous multi-source data extracted from geographic information system. For implementation of the objective of our study, the steps were taken in sequence as follows: (1) 2D road skeleton data were firstly extracted from the remote sensing images by means of a customized operation (including USM sharpening, segmentation, filtering, filling holes, thinning, curve fitting and removal of burrs); (2) 3D surfaces were generated by means of interpolation with a DEM; (3) a 3D digital highway model was reconstructed based on space vectors transformation. In addition, the resulting virtual road model was presented to reproduce the actual driving conditions in a virtual environment for driving simulators.

Language: en

Keywords

3D digital modeling; Digital elevation models; Driving simulator; Highway; Remote sensing images