TY - GEN
T1 - Deep Traffic Light Detection for Self-driving Cars from a Large-scale Dataset
AU - Kim, Jinkyu
AU - Cho, Hyunggi
AU - Hwangbo, Myung
AU - Choi, Jaehyung
AU - Canny, John
AU - Kwon, Youngwook Paul
N1 - Funding Information:
The authors would like to thank Jihyun Yoon and Chankyu Lee for their helpful comments and the anonymous reviewers of this paper. This work was supported in part by Samsung Scholarship.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/7
Y1 - 2018/12/7
N2 - Traffic lights perception problem is one of the key challenges for autonomous vehicle controllers in urban areas. While a number of approaches for traffic light detection have been proposed, these methods often require a prior knowledge of map and/or show high false positive rates. Recent successes suggest that deep neural networks will be widely used in self-driving cars, but current public datasets do not provide sufficient amount of labels for training such large deep neural networks. In this paper, we developed a two-step computational method that can detect traffic lights from images in a real-time manner. The first step exploits a deep neural object detection architecture to fine true traffic light candidates. In the second step, a point-based reward system is used to eliminate false traffic lights out of the candidates. To evaluate the proposed approach, we collected a human-annotated large-scale traffic lights dataset (over 60 hours). We also designed a real-world experiment with an instrumented self-driving vehicle and observed that the proposed method was able to handle false traffic lights substantially better compared with the baseline considered.
AB - Traffic lights perception problem is one of the key challenges for autonomous vehicle controllers in urban areas. While a number of approaches for traffic light detection have been proposed, these methods often require a prior knowledge of map and/or show high false positive rates. Recent successes suggest that deep neural networks will be widely used in self-driving cars, but current public datasets do not provide sufficient amount of labels for training such large deep neural networks. In this paper, we developed a two-step computational method that can detect traffic lights from images in a real-time manner. The first step exploits a deep neural object detection architecture to fine true traffic light candidates. In the second step, a point-based reward system is used to eliminate false traffic lights out of the candidates. To evaluate the proposed approach, we collected a human-annotated large-scale traffic lights dataset (over 60 hours). We also designed a real-world experiment with an instrumented self-driving vehicle and observed that the proposed method was able to handle false traffic lights substantially better compared with the baseline considered.
UR - http://www.scopus.com/inward/record.url?scp=85060460079&partnerID=8YFLogxK
U2 - 10.1109/ITSC.2018.8569575
DO - 10.1109/ITSC.2018.8569575
M3 - Conference contribution
AN - SCOPUS:85060460079
T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
SP - 280
EP - 285
BT - 2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018
Y2 - 4 November 2018 through 7 November 2018
ER -