Impacts of Special Traffic Lights on Deep Learning Based Traffic Light Recognition Systems 


Vol. 46,  No. 3, pp. 526-531, Mar.  2021
10.7840/kics.2021.46.3.526


PDF
  Abstract

Traffic light recognition is an essential task in autonomous driving and ADAS(ADAS: Advanced Driver Assistance Systems). Traffic light systems are similar in most countries but there exist special traffic signals adopted to specific countries which must be taken care of. In case of Korea, bus priority traffic lights are being for bus-only lanes. In this study, we analyze the impact of bus priority traffic lights on the performance of a traffic light detection system based on YOLOv3 deep learning model. That is, we evaluate the traffic light detection system trained with a dataset containing bus priority traffic lights which we have collected and discuss reasons behind comparatively low performances in detecting bus priority traffic lights.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

H. Kim, Y. Han, J. Park, "Impacts of Special Traffic Lights on Deep Learning Based Traffic Light Recognition Systems," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 3, pp. 526-531, 2021. DOI: 10.7840/kics.2021.46.3.526.

[ACM Style]

Hyeong-seok Kim, Young-Joo Han, and Joon-Sang Park. 2021. Impacts of Special Traffic Lights on Deep Learning Based Traffic Light Recognition Systems. The Journal of Korean Institute of Communications and Information Sciences, 46, 3, (2021), 526-531. DOI: 10.7840/kics.2021.46.3.526.

[KICS Style]

Hyeong-seok Kim, Young-Joo Han, Joon-Sang Park, "Impacts of Special Traffic Lights on Deep Learning Based Traffic Light Recognition Systems," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 3, pp. 526-531, 3. 2021. (https://doi.org/10.7840/kics.2021.46.3.526)