A Method of Traffic Lights Detection Based on Visual Selective Attention

DOI

10.2991/icismme-15.2015.173How to use a DOI?

Keywords

Visual attention; Image enhancement; Region of interest; Region labeling.

Abstract

In this paper, the candidate target traffic lights under different backgrounds were automatically detected with the visual selective attention mechanism. The region of interest in color image was projected into the gray, and the gray image enhancement was done through top-hat algorithm. The binary image was obtained by using Otsu’s method. And finally the logical ‘and’ operation was carried out for the binary image and the binary image which was obtained according to threshold segmentation in HSI space. The detection on depth information feature of the lights surrounded by the dark boundary was applied to the interested target candidate region. Experimental results show that this method was robust.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xueling Wang
AU  - Youfu Wu
AU  - Peng Yang
AU  - Zusheng Chen
PY  - 2015/07
DA  - 2015/07
TI  - A Method of Traffic Lights Detection Based on Visual Selective Attention
BT  - Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy
PB  - Atlantis Press
SP  - 827
EP  - 830
SN  - 1951-6851
UR  - https://doi.org/10.2991/icismme-15.2015.173
DO  - 10.2991/icismme-15.2015.173
ID  - Wang2015/07
ER  -