Abstract
Traffic light recognition is an essential task for an advanced driving assistance system (ADAS) as well as for autonomous vehicles. Recently, deep-learning has become increasingly popular in vision-based object recognition owing to its high performance of classification. In this study, we investigate how to design a deep-learning based high-performance traffic light detection system. Two main components of the recognition system are investigated: the color space of the input video and the network model of deep learning. We apply six color spaces (RGB, normalized RGB, Ruta’s RYG, YCbCr, HSV, and CIE Lab) and three types of network models (based on the Faster R-CNN and R-FCN models). All combinations of color spaces and network models are implemented and tested on a traffic light dataset with 1280×720 resolution. Our simulations show that the best performance is achieved with the combination of RGB color space and Faster R-CNN model. These results can provide a comprehensive guideline for designing a traffic light detection system.
Highlights
Over the past few years, various advanced driving assistance system (ADAS) have been developed and commercialized
We mainly focus on vision-based traffic light recognition using deep-learning
We focus on the combination of the color spaces and the ensemble networks which can achieve high performance of the traffic light detection
Summary
Over the past few years, various advanced driving assistance system (ADAS) have been developed and commercialized. Most automotive companies are doing their best to launch autonomous vehicles as soon as possible. The traffic light recognition is an essential task for ADAS as well as for autonomous vehicle. These can be analyzed from three aspects such as color space, feature extraction, and verification/classification. Some studies [15,16,17,18] have used more than one color spaces. Some basic deeplearning networks such as LeNet [33], AlexNet [34], and YOLO [35, 36] have been applied to traffic light recognition. Other approaches using visual light road-to-vehicle communication have been developed. We mainly focus on vision-based traffic light recognition using deep-learning
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
