Enhanced Traffic Light Detection Method Using Geometry Information

Authors: Changhwan Choi, Yongwan Park

Abstract:

In this paper, we propose a method that allows faster and more accurate detection of traffic lights by a vision sensor during driving, DGPS is used to obtain physical location of a traffic light, extract from the image information of the vision sensor only the traffic light area at this location and ascertain if the sign is in operation and determine its form. This method can solve the problem in existing research where low visibility at night or reflection under bright light makes it difficult to recognize the form of traffic light, thus making driving unstable. We compared our success rate of traffic light recognition in day and night road environments. Compared to previous researches, it showed similar performance during the day but 50% improvement at night.

Keywords: Traffic light, Intelligent vehicle, Night, Detection, DGPS (Differential Global Positioning System).

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1094303

References:

[1] Sebastian Thrun, Mike Montemerlo, HendrikDahlkamp, David Stavens, Andrei Aron, James Diebel, "Stanley: The Robot that Won the DARPA Grand Challenge,”Journal of Field Robotics, Vol.23, No.9, pp.661-692,2006.
[2] De Charette R, FawziNashashibi, "Real Time Visual Traffic Lights Recognition Based Spot Light Detection and Adaptive Traffic Lights Templates,”IEEE Intelligent Vehicles Symposium, Xi’an, 2009, pp.358-363.
[3] ZixingCai, Ti Li, MingqinGu, "Real-time Recognition System of Traffic Light in Urban Environment,”IEEE Symposium on Computational Intelligence for Security and Defence Applications, Ottawa, 2012, pp.1-6.
[4] Masako Omachi, Shinichiro Omachi, "Detection of Traffic Light Using Structureal Information,”IEEE 10th International Conference on Signal Processing, Beijing, 2010, pp.809-812.
[5] Biswas. R, Khan. A, Alom. M.Z, Khan. M, "Night mode prohibitory traffic signs detection”, IEEE International Conference on Informatics, Electronics & vision, Dhaka, 2013, pp.1-5.
[6] Mossi.J.M.,Albiol. A, Ornedo. V.N, "Real-time Traffic Analysis at Night-time”, 18th IEEE International Conference on Image Processing, Brussels, 2011, pp.2941-2944.
[7] Tzu-Pin Sung, Hsin-Mu Tsai, "Real-time Traffic Light Recognition on Mobile devices with Geometry-based filtering”, 7th International Conference on Distributed Smart Cameras, Palm Springs, 2013, pp.1-7.
[8] Nathaniel Fairfield, Chris Urmson, "Traffic Light Mapping and Detection,”IEEE International Conference on Robotics and Automation,Shanghai, 2011, pp.5421-5426.
[9] Levinson J, Askeland J, Dolson J, Thrun S, "Traffic Light Mapping, Localization, and State Detection for Autonomous Vehicles,” IEEE International Conference on Robotics and Automation, Shanghai, 2011, pp.5784-5791.
[10] Gyungsueng Yang, Gueesang Lee, "The Detection of Signals for Auto Navigation,”Institute of Electronics Engineers of Korea Fall Conference, , Seoul, 1996, pp.1456-1459.
[11] Omachi. M, Omachi. S, "Traffic light detection with color and edge information”, 2nd IEEE International conference on Computer Science and Information Technology, Beijing, 2009, pp.284-287.