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


6
Oct

Open seminar with Mistra SAMS international scientific advisory...

Mistra SAMS international scientific advisory panel (ISAP) is visiting Stockholm, and the program will host an open seminar where the panel members will give talks in their area of expertise.
19-20
Oct

ERPUG 2017

The five year anniversary of  European Road Profile Users' Group (ERPUG) Forum will take place at Ramboll head quarter, Copenhagen, Denmark October 19-20, 2017. 

LATEST NEWS


2017-07-05

Vehicle Driver Monitoring: sleepiness and cognitive load

To prevent road crashes it is important to understand driver related contributing factors, which have been suggested to be the critical reason in 94 per cent of crashes. The overall aim of the project Vehicle Driver Monitoring has been to advance the...


2017-06-29

Tomas Svensson new director-general

Tomas Svensson was today appointed Director-General of VTI. Tomas has been acting Director-General since January 2017. 


2017-05-30

Crash testing bicycles at VTI

For the first time single bicycle crashes have been simulated at the VTI crash safety laboratory.


2017-05-15

A case study exploring firefighters’ and municipal officials’ preparedness for electrical vehicles

A VTI-study presents a social perspective on new vehicle technology. It explores the self-reported preparedness of the fire departments (i.e., rescue services) in Sweden’s three largest cities regarding rescue operations involving electrical vehicles (EVs).


2017-05-02

Pioneering research on and about bicycles at VTI

Under what circumstances might cyclists lose tyre grip? What actions could then be taken to prevent a crash? VTI is currently developing a theoretical model of the behaviour of bicycle tyres during braking and steering in different situations and on different...


2017-05-02

Virtual pedestrians create efficient stations

If more people are to choose sustainable travel, then the public transport stations of the future must be designed so that pedestrians can get where they are going quickly, without congestion or queues. The Swedish Road and Transport Research Institute (VTI)...