Int J Performability Eng ›› 2020, Vol. 16 ›› Issue (8): 1203-1214.doi: 10.23940/ijpe.20.08.p7.12031214

Previous Articles     Next Articles

Dual Model-based Traffic Light and Sign Detection using Prior Information

Weiguo Pana,b,*, Feng Panb, and En Fua,b   

  1. aBeijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China;
    bCollege of Robotics, Beijing Union University, Beijing, 100101, China
  • Submitted on ; Revised on ; Accepted on
  • Contact: *E-mail address: asherbuu@163.com
  • About author:Weiguo Pan is a lecturer at Beijing Union University. His research interests include object detection and computer vision.Feng Pan is an associate professor at Beijing Union University. His research interests include semi-supervised machine learning and navigation.En Fu is a graduate student at Beijing Union University. His research interests include object detection and machine learning.

Abstract: Traffic light and traffic sign detection are important in the field of self-driving. They can guide vehicles to drive safely on the road. It is difficult for existing algorithms of object detection to detect targets simultaneously and achieve high accuracy. In this paper, a dual-model framework is proposed to detect traffic light and signs for a self-driving vehicle based on prior information. This framework can switch the detection model according to the prior information. The color information of the traffic sign is used to extract the ROI and improve the detection efficiency. The work of this paper also includes collecting and annotating a large amount of image data to apply the model trained on the proposed framework to self-driving. The proposed framework is verified on a real road test of a self-driving vehicle.

Key words: traffic light, traffic sign, self-driving, prior information, object detection