Intelligent Traffic Incidents Detection Method in Freeway Corridors

DOI

10.2991/meic-15.2015.371How to use a DOI?

Keywords

traffic incident detection; freeway corridors; intelligent detection; wireless sensors; support vector machines (SVM)

Abstract

Traffic incidents detection has become an important issue in the past decades, which would result in a large amount financial cost and considerable reduction in traffic efficiency. Most previous studies mainly pay their attention on automatic incident detection in freeway corridors based on the traffic data collected by inductive loops or video monitors. In this paper, we have presented a support vector machines (SVM)-based method to confirm whether a traffic incident occurs or incident-free in freeway corridors with the utilization of the real-time traffic data collected and transmitted by wireless sensors. We also have extracted the most crucial traffic variables as features and utilized them into the SVM model for data process. Several experiments have been conducted to evaluate our method’s performance compared with a representative relevant work, in terms of detection rate, mean time-to-detect and false alarm rate. The experimental results depict that our method could obtain better performance in most case.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Binbin Zhou
AU  - Hexin Lv
AU  - Tiaojuan Ren
AU  - Yourong Chen
AU  - Ning Qiu
PY  - 2015/04
DA  - 2015/04
TI  - Intelligent Traffic Incidents Detection Method in Freeway Corridors
BT  - Proceedings of the 2015 International Conference on Mechatronics, Electronic, Industrial and Control Engineering
PB  - Atlantis Press
SP  - 1623
EP  - 1626
SN  - 2352-5401
UR  - https://doi.org/10.2991/meic-15.2015.371
DO  - 10.2991/meic-15.2015.371
ID  - Zhou2015/04
ER  -