Current Status and Issues of Traffic Light Recognition Technology in Autonomous Driving System

Naoki SUGANUMA; Keisuke YONEDA

doi:10.1587/transfun.2021WBI0002

IEICE TRANSACTIONS on Fundamentals

Open Access
Current Status and Issues of Traffic Light Recognition Technology in Autonomous Driving System

Naoki SUGANUMA, Keisuke YONEDA

Full Text Views

53

Cite this

Free PDF (3.1MB)

Summary :

Autonomous driving technology is currently attracting a lot of attention as a technology that will play a role in the next generation of mobility. For autonomous driving in urban areas, it is necessary to recognize various information. Especially, the recognition of traffic lights is important in crossing intersections. In this paper, traffic light recognition technology developed by the authors was evaluated using onboard sensor data during autonomous driving in the Tokyo waterfront area as an example of traffic light recognition technology. Based on the results, it was found that traffic lights could be recognized with an accuracy of approximately 99% to carry out the decision making for intersection approaching. However, from the evaluation results, it was also confirmed that traffic light recognition became difficult under situations involving occlusion by other object, background assimilation, nighttime conditions, and backlight by sunlight. It was also confirmed that these effects are mostly temporary, and do not significantly affect decision-making to enter intersections as a result of utilizing information from multiple traffic lights installed at an intersection. On the other hand, it is expected that recognition with current onboard cameras will become technically difficult during situations in which not all traffic lights are visually recognizable due to the effects of back or front light by sunlight when stopped at the stop line of an intersection. This paper summarizes these results and presents the necessity of appropriate traffic light installation on the assumption of recognition by onboard cameras.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E105-A No.5 pp.763-769

Publication Date: 2022/05/01

Publicized: 2021/10/12

Online ISSN: 1745-1337

DOI: 10.1587/transfun.2021WBI0002

Type of Manuscript: Special Section INVITED PAPER (Special Section on Intelligent Transport Systems and Wideband Systems for Smart Cities and Mobility)

Category

Authors

Naoki SUGANUMA
Kanazawa University
Keisuke YONEDA
Kanazawa University

Keyword

traffic light recognition, autonomous driving, image processing, SIP-adus

Cite this

Copy

Naoki SUGANUMA, Keisuke YONEDA, "Current Status and Issues of Traffic Light Recognition Technology in Autonomous Driving System" in IEICE TRANSACTIONS on Fundamentals, vol. E105-A, no. 5, pp. 763-769, May 2022, doi: 10.1587/transfun.2021WBI0002.
Abstract: Autonomous driving technology is currently attracting a lot of attention as a technology that will play a role in the next generation of mobility. For autonomous driving in urban areas, it is necessary to recognize various information. Especially, the recognition of traffic lights is important in crossing intersections. In this paper, traffic light recognition technology developed by the authors was evaluated using onboard sensor data during autonomous driving in the Tokyo waterfront area as an example of traffic light recognition technology. Based on the results, it was found that traffic lights could be recognized with an accuracy of approximately 99% to carry out the decision making for intersection approaching. However, from the evaluation results, it was also confirmed that traffic light recognition became difficult under situations involving occlusion by other object, background assimilation, nighttime conditions, and backlight by sunlight. It was also confirmed that these effects are mostly temporary, and do not significantly affect decision-making to enter intersections as a result of utilizing information from multiple traffic lights installed at an intersection. On the other hand, it is expected that recognition with current onboard cameras will become technically difficult during situations in which not all traffic lights are visually recognizable due to the effects of back or front light by sunlight when stopped at the stop line of an intersection. This paper summarizes these results and presents the necessity of appropriate traffic light installation on the assumption of recognition by onboard cameras.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021WBI0002/_p

Copy

@ARTICLE{e105-a_5_763,
author={Naoki SUGANUMA, Keisuke YONEDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Current Status and Issues of Traffic Light Recognition Technology in Autonomous Driving System},
year={2022},
volume={E105-A},
number={5},
pages={763-769},
abstract={Autonomous driving technology is currently attracting a lot of attention as a technology that will play a role in the next generation of mobility. For autonomous driving in urban areas, it is necessary to recognize various information. Especially, the recognition of traffic lights is important in crossing intersections. In this paper, traffic light recognition technology developed by the authors was evaluated using onboard sensor data during autonomous driving in the Tokyo waterfront area as an example of traffic light recognition technology. Based on the results, it was found that traffic lights could be recognized with an accuracy of approximately 99% to carry out the decision making for intersection approaching. However, from the evaluation results, it was also confirmed that traffic light recognition became difficult under situations involving occlusion by other object, background assimilation, nighttime conditions, and backlight by sunlight. It was also confirmed that these effects are mostly temporary, and do not significantly affect decision-making to enter intersections as a result of utilizing information from multiple traffic lights installed at an intersection. On the other hand, it is expected that recognition with current onboard cameras will become technically difficult during situations in which not all traffic lights are visually recognizable due to the effects of back or front light by sunlight when stopped at the stop line of an intersection. This paper summarizes these results and presents the necessity of appropriate traffic light installation on the assumption of recognition by onboard cameras.},
keywords={},
doi={10.1587/transfun.2021WBI0002},
ISSN={1745-1337},
month={May},}

Copy

TY - JOUR
TI - Current Status and Issues of Traffic Light Recognition Technology in Autonomous Driving System
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 763
EP - 769
AU - Naoki SUGANUMA
AU - Keisuke YONEDA
PY - 2022
DO - 10.1587/transfun.2021WBI0002
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 2022
AB - Autonomous driving technology is currently attracting a lot of attention as a technology that will play a role in the next generation of mobility. For autonomous driving in urban areas, it is necessary to recognize various information. Especially, the recognition of traffic lights is important in crossing intersections. In this paper, traffic light recognition technology developed by the authors was evaluated using onboard sensor data during autonomous driving in the Tokyo waterfront area as an example of traffic light recognition technology. Based on the results, it was found that traffic lights could be recognized with an accuracy of approximately 99% to carry out the decision making for intersection approaching. However, from the evaluation results, it was also confirmed that traffic light recognition became difficult under situations involving occlusion by other object, background assimilation, nighttime conditions, and backlight by sunlight. It was also confirmed that these effects are mostly temporary, and do not significantly affect decision-making to enter intersections as a result of utilizing information from multiple traffic lights installed at an intersection. On the other hand, it is expected that recognition with current onboard cameras will become technically difficult during situations in which not all traffic lights are visually recognizable due to the effects of back or front light by sunlight when stopped at the stop line of an intersection. This paper summarizes these results and presents the necessity of appropriate traffic light installation on the assumption of recognition by onboard cameras.
ER -

IEICE TRANSACTIONS on Fundamentals