Citation

Kim HK, Yoo KY, Park JH, Jung HY. Sensors (Basel) 2019; 19(7): s19071700.

Affiliation

Department of Information and Communication Engineering, Yeungnam University, Gyeongsan 38544, Korea. hoyoul@yu.ac.kr.

Copyright

(Copyright © 2019, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s19071700

PMID

30974735

Abstract

A traffic light recognition system is a very important building block in an advanced driving assistance system and an autonomous vehicle system. In this paper, we propose a two-staged deep-learning-based traffic light recognition method that consists of a pixel-wise semantic segmentation technique and a novel fully convolutional network. For candidate detection, we employ a binary-semantic segmentation network that is suitable for detecting small objects such as traffic lights. Connected components labeling with an eight-connected neighborhood is applied to obtain bounding boxes of candidate regions, instead of the computationally demanding region proposal and regression processes of conventional methods. A fully convolutional network including a convolution layer with three filters of (1 × 1) at the beginning is designed and implemented for traffic light classification, as traffic lights have only a set number of colors. The simulation results show that the proposed traffic light recognition method outperforms the conventional two-staged object detection method in terms of recognition performance, and remarkably reduces the computational complexity and hardware requirements. This framework can be a useful network design guideline for the detection and recognition of small objects, including traffic lights.

Language: en

Keywords

advanced driver assistance system; artificial neural networks; binary semantic segmentation; deep learning; traffic light detection; traffic light recognition