Efficient Ego Lane Detection for Various LaneTypes
Rebekka Charlotte Peter, Yuduo Song, Martin Lauer
Kapitel/Beitrag aus dem Buch: Heizmann M. & Längle T. 2020. Forum Bildverarbeitung 2020.
Kapitel/Beitrag aus dem Buch: Heizmann M. & Längle T. 2020. Forum Bildverarbeitung 2020.
In this work, we present an ego lane detector designed
for the use in automotive vision systems for personal
light electric vehicles like electric bicycles, tricycles or scooters.
The approach is based on a combination of gradientbased
line detection, color-based segmentation and geometrical
rules, making the ego lane detector fast, but also robust
to different scenes, including curves. Qualitative evaluation
on over fifty traffic scenes show that the lane detector is able
to find a suitable approximation of the road area with an IoU
of 75.71%.
Peter, R et al. 2020. Efficient Ego Lane Detection for Various LaneTypes. In: Heizmann M. & Längle T (eds.), Forum Bildverarbeitung 2020. Karlsruhe: KIT Scientific Publishing. DOI: https://doi.org/10.58895/ksp/1000124383-33
This chapter distributed under the terms of the Creative Commons Attribution + ShareAlike 4.0 license. Copyright is retained by the author(s)
Dieses Buch ist Peer reviewed. Informationen dazu Hier finden Sie mehr Informationen zur wissenschaftlichen Qualitätssicherung der MAP-Publikationen.
Veröffentlicht am 25. November 2020