Paper
16 February 2023 Night-time lane positioning based on camera and LiDAR fusion
Shengke Niu, Yilin Ma, Chong Wei
Author Affiliations +
Proceedings Volume 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022); 125911H (2023) https://doi.org/10.1117/12.2668596
Event: 6th International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 2022, Guangzhou, China
Abstract
Accurate perception of lane lines position and lane width is a key factor in driver assistance systems. At the same time, night driving is an important driving scene. Therefore, this paper proposes a night-time lane lines positioning method based on camera and LiDAR fusion. The lane lines are detected in the image by using computer vision, and the road surface equation is established based on the deep fusion of image and point cloud data. Combining these two aspects, the position of the lane lines in the 3D space can be solved. According to the positioning results, the distance between the vehicle and the lane lines and the lane width can be obtained. After testing the actual collected data sets, the method can achieve 99% accuracy after testing, and the maximum error is within 3%. The proposed method integrates the image and point cloud information, completes the road surface point cloud and uses the road surface as the limiting condition of lane lines positioning to make the positioning result more accurate. The method can bring positive effect to traffic scene perception under night driving.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shengke Niu, Yilin Ma, and Chong Wei "Night-time lane positioning based on camera and LiDAR fusion", Proc. SPIE 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 125911H (16 February 2023); https://doi.org/10.1117/12.2668596
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Roads

Point clouds

Cameras

LIDAR

Autonomous driving

Hough transforms

Image processing

Back to Top