Authors:
Sven Eckelmann
1
;
Toralf Trautmann
2
;
Xinyu Zhang
1
and
Oliver Michler
1
Affiliations:
1
Institute of Traffic Telematics, Technical University Dresden, Dresden, Germany
;
2
Mechatronics Department, University of Applied Science Dresden, Dresden, Germany
Keyword(s):
LiDAR, Point Clouds, Retro Reflecting, Lane Marking, 3M, Camera.
Abstract:
Highly automated driving requires a zero-error interpretation of the current vehicle environment utilizing state of the art environmental perception based on camera and Light Detection And Ranging (LiDAR) sensors. An essential element of this perception is the detection of lane markings, e.g. for lane departure warnings. In this work, we empirically evaluate a novel kind of lane marking, which enhances the contrast (artificial light-dark boundary) for cameras and 3D retro reflective elements guarantee a better reflection for light beams from a LiDAR. Thus intensity of point data from LiDAR is regarded directly as a feature for lane segmentation. In addition, the 3D lane information from a 2D camera is estimated using the intrinsic and extrinsic camera parameters and the lane width. In the frame of this paper, we present the comparison between the detection based on camera and LiDAR as well as the comparison between conventional and the new lane marking in order to improve the reliabi
lity of lane detection for different sensors. As a result, we are able to demonstrate that the track can be detected safely with the LiDAR and the new lane marking.
(More)