masterhead masterhead  masterhead

Traffic Light Detection Using High-speed Vision


Automatic traffic light detection plays an important role for driver-assistance system and autonomous vehicles. Based on the fact that LED traffic light flashes in proportion to the input AC power frequency, we propose a traffic light detection method which focuses on the flash pattern extraction using high-speed vision. Exploiting temporal information is shown to be very effective in the experiments. It is considered to be more robust than visual information-only methods.


  1. Taku Senoo, Chia-Hui Chen, Norimasa Kishi, Masatoshi Ishikawa: Traffic Light Detection Based on Flash Pattern Extraction Using High-speed Vision, 19th SICE System Integration Division Annual Conference(SI2018) (Osaka, Japan, 2018.12.15) / Proceedings, pp.1235-1241 (2018).
  2. Z. Wu, Y. Watanabe and M. Ishikawa: Hybrid led traffic light detection using high-speed camera, Proc. of IEEE Int. Conf. on Intelligent Transportation Systems, pp. 1235-1241, 2016.
Ishikawa Senoo Laboratory, Department of Information Physics and Computing, Department of Creative Informatics,
Graduate School of Information Science and Technology, University of Tokyo
Ishikawa Senoo Laboratory WWW admin:
Copyright © 2008 Ishikawa Senoo Laboratory. All rights reserved.