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


25-26
Apr

Cost Benefit Analysis (CBA) workshop in Stockholm

An open seminar and workshop in Stockholm will be held on 25-26 April 2018. The workshop deals with the use of CBA as a basis for decision-making in the public sector. The workshop is organized by, among others, Professor Jan-Eric Nilsson, VTI.
13-14
Jun

The 6st Humanist Conference

The 6th HUMANIST Conference will take place 13-14 June 2018 in the Hague, The Netherlands. The scope of the conference covers a wide range of topics on Human Factors in Transport. Tania Willstrand and Alexander Eriksson will present their research results.

LATEST NEWS


2018-04-17

VTI will develop simulators for ambulance staff

VTI has initiated a pilot study for paramedics with the Centre for Teaching & Research in Disaster Medicine and Traumatology and Linköping University. The aim is to give ambulance staff the opportunity to practice critical medical tasks in a moving vehicle in...


2018-04-12

Unique electrified road opens in Sweden

The world’s first electrified road recharging the batteries of cars and trucks while driving opened in Sweden. The Swedish Minister for Infrastructure, Tomas Eneroth, was at the formal inauguration of the electrified road on April 11, 2018. VTI is one of 22...


2018-04-11

Swedish road safety spreads internationally

Sweden is a leading country in terms of road safety, and the research conducted by the Swedish National Road and Transport Research Institute (VTI) has contributed to increased safety. VTI’s remit includes disseminating research results and keeping up to date...


2018-04-06

A greater understanding of cyclists' behaviour

Cyclists are often accused of not following traffic rules and being hooligans on the road. New research shows that there is no support for this perception. "Our observations reveal no such general anarchy" says Sonja Forward, researcher at VTI.


2018-03-28

New technology for road surface measurement tested

VTI has tested a new scanning-laser technology for road surface measurement. The tests show the new technology for comprehensive transverse-profile measurement provides dependable values in measuring transverse profile and rut depth.


2018-03-15

Ulf Sandberg has been presented with the TTI Lifetime Achievement Award 2018

VTI’s Senior Research Leader Ulf Sandberg has been presented with the TTI Lifetime Achievement Award 2018 for his work on research into tyres and road surface.