@article{ref1,
title="Traffic light recognition based on binary semantic segmentation network",
journal="Sensors (Basel)",
year="2019",
author="Kim, Hyun-Koo and Yoo, Kook-Yeol and Park, Ju H. and Jung, Ho-Youl",
volume="19",
number="7",
pages="s19071700-s19071700",
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.<p /> <p>Language: en</p>",
language="en",
issn="1424-8220",
doi="10.3390/s19071700",
url="http://dx.doi.org/10.3390/s19071700"
}