A Fast Lane Detection and Tracking Algorithm

DOI

10.2991/ifmeita-16.2016.112How to use a DOI?

Keywords

laneï¼›linear modelï¼›coordination detectionï¼›Hough transformationï¼›directional filter

Abstract

To improve the real time performance and robustness, an algorithm about lane coordination detection is proposed. The lane parameter is detected by the local windows extraction and the global extraction based on Hough transformation, with the help of the lane parameter confidence interval and the active box of interest. The algorithm is conducted including the below steps. First, set two groups of active boxes of interest; second, filter directionally; third, scan the number of lines in the interest box. The candidate points are selected to fit a straight line if the points have the max gradient. The experimental results show that the proposed scheme is accurate, robust and fast enough for the requirements of real time.

Copyright

© 2016, 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  - Huifen Dong
AU  - Mingbo Hu
PY  - 2016/01
DA  - 2016/01
TI  - A Fast Lane Detection and Tracking Algorithm
BT  - Proceedings of the 2016 International Forum on Management, Education and Information Technology Application
PB  - Atlantis Press
SP  - 608
EP  - 613
SN  - 2352-5398
UR  - https://doi.org/10.2991/ifmeita-16.2016.112
DO  - 10.2991/ifmeita-16.2016.112
ID  - Dong2016/01
ER  -