Study of the Recognition and Tracking Methods for Lane Lines Based on Image Edge Detections

DOI

10.2991/cecs-18.2018.33How to use a DOI?

Keywords

Lane line detection, Constrained Hough transform,Extended Kalman filter, Lane tracking.

Abstract

In order to realize the real-time accurate recognition and tracking of lane lines for self-driving cars, an improved Hough transform method for lane line recognition and fitting has been introduced based on the preprocessing of current frame lane line image. The extended Kalman filter is used to study the initial prediction and correction adjustments on the next frame lane line image. The relative distance between the vehicle and the lane line is to be obtained by the calculation of deviation rate. Then the detection and tacking of the lane line are realized. Experimental results prove that the introduced methods can effectively detect, recognize, and track the lane line for self-driving cars with lower false detection rate and real-time detection abilities.

Copyright

© 2018, 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  - Weijiao Yang
AU  - Xianhai Yang
AU  - Yudong Wei
AU  - Xiang Cheng
PY  - 2018/07
DA  - 2018/07
TI  - Study of the Recognition and Tracking Methods for Lane Lines Based on Image Edge Detections
BT  - Proceedings of the 2018 International Symposium on Communication Engineering & Computer Science (CECS 2018)
PB  - Atlantis Press
SP  - 179
EP  - 185
SN  - 2352-538X
UR  - https://doi.org/10.2991/cecs-18.2018.33
DO  - 10.2991/cecs-18.2018.33
ID  - Yang2018/07
ER  -