Watch the traffic signal: a signal state extraction system for naturalistic driving videos

Dongxi Zheng
Madhav V. Chitturi
David A. Noyce
John Lee

Naturalistic driving studies (NDS) are revolutionizing road safety research. Naturalistic driving data provide a new window into driver behavior that promises a deeper understanding than was ever possible with crash data, roadside observations, or driving simulator experiments. NDS collect extensive vehicle network data, vehicle internal videos (e.g., drivers and passengers), and vehicle external videos (e.g., forward roadway). The video record of the driver and surrounding road situation often provide a more revealing account of driver behavior. Data size becomes a double edged sword for most NDS. Fully or partially automated procedures are needed for data reduction. Both intentional and unintentional violations of traffic signals can cause severe consequences, like fatal right-angle crashes. Knowing the signal state when the driver navigated through the intersection is the first step towards judging the driver’s compliance and analyzing deeper human factors issues. A system that codes traffic signal state from georeferenced front-view videos was developed for use with the Second Strategic Highway Research Program (SHRP2) NDS data. GPS coordinates and a free online map database are used to identify candidate frames from lengthy videos for computer vision processing. The computer vision algorithm uses color histograms and shape matching to detect traffic signals. Vehicle movement is used to select, from multiple signals the one corresponding to the vehicle’s traffic lane. Temporal relationship between frames is employed for the purpose of refining detection results. Experiments were conducted on daytime videos and showed reasonable performance given the severe challenges posed by the SHRP2 data. Misclassifications were primarily due to other vehicles’ taillights, reddish yellow signals, yellowish red signals, green traffic signs, etc. Misses were due to distant frames with very few pixels corresponding to the signals and reduced color conspicuity compared to background scenes (e.g., green signals and the sky look similar). The system is an insightful first step towards using computer vision techniques to support signal state coding of the large volumes of naturalistic driving video data. Challenges revealed by the experimental results are valuable knowledge for future improvement.

MEET US


5-6
Dec

Vision Zero for Sustainable Road Safety in the Baltic Sea Region

The conference Vision Zero for Sustainable Road Safety in the Baltic Sea Region is held i Vilnius, Lithuania. VTI is part of the organisation committé and also one of the speakers.

LATEST NEWS


2018-10-05

Users contribute to the development of train simulators

Apart from advanced driving simulators, VTI has developed several variations of train simulators which are used for training, education and research. In recent years, interest has increased drastically among major actors in the railway sector, and VTI has...


2018-10-03

VR study to contribute to a better working environment for bus drivers

A study where bus drivers test autonomous driving in a VR environment may contribute to a better working environment with reduced stress on the driver and safer driving.


2018-10-02

Non-native plant species spread via transport systems

Researchers at VTI have compiled a report on non-native invasive plant species in Sweden and how they spread via transport systems.


2018-09-20

EU-project VIRTUAL: improving road safety with virtual crash tests

Crash tests are used to improve safety on roads. Therefore the EU now funds a research project to develop virtual methods of crash testing. VTI coordinates the project, called VIRTUAL. The project now invites experts interested in Human Body Modeling to join...


2018-08-28

EU project protects cyclists and pedestrians

According to the World Health Organisation, more than one quarter of road traffic fatalities in 2010 were pedestrians and cyclists. Every year, about 335,000 unprotected road users die because of traffic accidents, which shows the scale of the problem. The EU...


2018-08-21

Swedish organisations in EU project on traffic safety and crash testing

Crash safety testing is one of the tools used to improve safety on roads. The EU is therefore funding a research project that started recently to develop virtual methods of crash testing. The long-term goal is to supplement the physical evaluation of crash...