Result Details
Analysis of Vehicle Trajectories for Determining Cross-Sectional Load Density Based on Computer Vision
Juránek Roman, Ing., Ph.D., DCGM (FIT)
Herout Adam, prof. Ing., Ph.D., DCGM (FIT)
NOVÁK, J.
HAVRÁNEK, P.
The goal of this work was to analyze the behavior of vehicles on third-grade roads with and without horizontal lane markings with small curvature (R <= 200m). The roads are not frequented by many vehicles, and therefore, a general short-term study would not be able to provide enough data. We used recording devices for long-term (weeks) recording of the traffic and designed a system for analyzing the trajectories of the vehicles employing computer vision. We collected a dataset at 6 distinct locations, containing 1 010 hours of day-time video. In this dataset, we tracked over 12 000 cars and analyzed their trajectories. The results show that the selected approach is functional and provides information that would be hard to mine otherwise. After application of the horizontal markings, the drivers slowed down and shifted slightly towards the outer side of the curvature.
Road Safety, Lane Markings, Trajectory Analysis, Computer Vision, Vehicle Tracking
@inproceedings{BUT161457,
author="ŠPAŇHEL, J. and JURÁNEK, R. and HEROUT, A. and NOVÁK, J. and HAVRÁNEK, P.",
title="Analysis of Vehicle Trajectories for Determining Cross-Sectional Load Density Based on Computer Vision",
booktitle="2019 22th International Conference on Intelligenet Transportation Systems (ITSC)",
year="2019",
pages="1001--1006",
publisher="Institute of Electrical and Electronics Engineers",
address="Auckland",
doi="10.1109/ITSC.2019.8917374",
isbn="978-1-5386-7024-8",
url="https://ieeexplore.ieee.org/document/8917374"
}Zpracování, zobrazování a analýza multimediálních a 3D dat, BUT, Vnitřní projekty VUT, FIT-S-17-3984, start: 2017-03-01, end: 2020-02-29, completed