Night-time lane positioning based on camera and LiDAR fusion

Shengke Niu; Yilin Ma; Chong Wei

doi:10.1117/12.2668596

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.

Citation Download Citation

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

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE