Road obstacle detection algorithm based on LiDAR point cloud

Xiaoyang Tan; Ziye Wang; Changhao Piao

doi:10.1117/12.2637507

13 May 2022 Road obstacle detection algorithm based on LiDAR point cloud

Xiaoyang Tan, Ziye Wang, Changhao Piao

Proceedings Volume 12248, Second International Conference on Sensors and Information Technology (ICSI 2022); 122481C (2022) https://doi.org/10.1117/12.2637507
Event: 2nd International Conference on Sensors and Information Technology (ICSI 2022), 2022, Nanjing, China

Abstract

For the problem of traditional 16-beam LiDAR has low detection accuracy for obstacles on the road, this paper developed an improved DBSCAN clustering algorithm, which can dynamically select the threshold parameters according to the distance between the point cloud and the LiDAR, so as to detect obstacles quickly and accurately. Fistly, according to the geometric features of the point cloud, the road curb points are extracted and the left and right roadside lines are fitted. Then, the region of interest is extracted based on the two lines. After the ground segmentation on the region of interest, the improved DBSCAN clustering algorithm is applied to complete the detection. Experiments show that this method can cluster the near and far obstacles quickly and accurately.

Citation Download Citation

Xiaoyang Tan, Ziye Wang, and Changhao Piao "Road obstacle detection algorithm based on LiDAR point cloud", Proc. SPIE 12248, Second International Conference on Sensors and Information Technology (ICSI 2022), 122481C (13 May 2022); https://doi.org/10.1117/12.2637507

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

Includes PDF, HTML & Video, when available