Lane Detection Algorithm Based on Road Structure and Extended Kalman Filter

Jinsheng Xiao, Wenxin Xiong, Yuan Yao, Liang Li, Reinhard Klette

Source Title: International Journal of Digital Crime and Forensics (IJDCF)12(2)

ISSN: 1941-6210|EISSN: 1941-6229|EISBN13: 9781799805809|DOI: 10.4018/IJDCF.2020040101

MLA

Xiao, Jinsheng, et al. "Lane Detection Algorithm Based on Road Structure and Extended Kalman Filter." IJDCF vol.12, no.2 2020: pp.1-20. http://doi.org/10.4018/IJDCF.2020040101

APA

Xiao, J., Xiong, W., Yao, Y., Li, L., & Klette, R. (2020). Lane Detection Algorithm Based on Road Structure and Extended Kalman Filter. International Journal of Digital Crime and Forensics (IJDCF), 12(2), 1-20. http://doi.org/10.4018/IJDCF.2020040101

Chicago

Xiao, Jinsheng, et al. "Lane Detection Algorithm Based on Road Structure and Extended Kalman Filter," International Journal of Digital Crime and Forensics (IJDCF) 12, no.2: 1-20. http://doi.org/10.4018/IJDCF.2020040101

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

Lane detection still demonstrates low accuracy and missing robustness when recorded markings are interrupted by strong light or shadows or missing marking. This article proposes a new algorithm using a model of road structure and an extended Kalman filter. The region of interest is set according to the vanishing point. First, an edge-detection operator is used to scan horizontal pixels and calculate edge-strength values. The corresponding straight line is detected by line parameters voted by edge points. From the edge points and lane mark candidates extracted above, and other constraints, these points are treated as the potential lane boundary. Finally, the lane parameters are estimated using the coordinates of the lane boundary points. They are updated by an extended Kalman filter to ensure the stability and robustness. Results indicate that the proposed algorithm is robust for challenging road scenes with low computational complexity.