Abstract
As the core of environmental perception, 3D target detection has always been the research focus of the majority of scientific researchers, and the use of point clouds obtained by lidar to detect the surrounding environment is the current mainstream 3D target detection technology. However, due to the influence of scanning environment, test distance, self-resolution and other factors, the original laser point clouds has a lot of noise and interference, so it is inconvenient to directly use for feature extraction and detection. Therefore, this paper preprocesses the point clouds of a vehicle lidar, and improves the traditional Euclidean clustering algorithm on this basis. Finally, a real vehicle experiment was carried out. Experiments show that compared with the traditional algorithm, the improved algorithm can more effectively cluster and segment distant nearby objects and occluded objects.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Junjing, Z.: Research on key technologies of intelligent vehicle target recognition and tracking based on lidar. Beijing University of Technology (2014)
Wangjang, Y.: Research on dynamic obstacle detection and recognition of unmanned vehicles based on lidar. Harbin Institute of Technology (2020)
Zhimei, G., Chunxiang, W., Ming, Y.: Vehicle tracking and identification method based on lidar. J. Shanghai Jiao Tong Univ. 43(06), 923–926 (2009)
Yanan, D., Zhaoxing, T., Liqiang, G.: Key technology of on-board lidar point clouds data processing. Comput. Measur. Control 30(01), 234–238 (2022)
Jinbo, Q.: Research on denoising method of 3D laser point clouds data based on clustering algorithm. Shenyang Jianzhu University (2020)
Guibin, C., Zhenhai, G., He, L.: Step-by-step automatic calibration algorithm for external parameters of vehicle-mounted 3D lidar. Chinese Laser 44(10), 249–55 (2017)
Feng, Z., Zhongben, T., Zufeng, Z., Hanwen, G.: 3D dynamic object detection algorithm for voxel point clouds fusion. J. Comput. Aid. Design Graph. 20, 1–13 (2022)
Bing, Z., Peng, C., Denghong, L.: A fast ground point clouds segmentation algorithm based on raster projection. Urban Surv. 30(03), 112–116 (2021)
Shaoquan, F., Xianghong, H., Chengwen, D., Cheng, L., Wei, W.: An adaptive slope threshold ground point clouds segmentation method. Surv. Map. Sci. 46(01), 156–161 (2021)
Fuqiang, L., Shihua, T., Guanghuan, H., Jinlong, M.: Airborne lidar building point clouds extraction and monomerization based on density noise application spatial clustering algorithm. Sci. Technol. Eng. 22(09), 3446–3452 (2022)
Acknowledgment
This work is supported by Fujian Provincial Natural Science Foundation (Grant No.:2021J1851) and Xiamen Winjoin Technology Corporation (Contract No.:S21228).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yue, P., Chen, N., Wang, S., Yu, S., Wang, Q., Liao, N. (2023). Research on a Processing Method of LiDAR Point Clouds. In: Wang, Y., Yu, T., Wang, K. (eds) Advanced Manufacturing and Automation XII. IWAMA 2022. Lecture Notes in Electrical Engineering, vol 994. Springer, Singapore. https://doi.org/10.1007/978-981-19-9338-1_21
Download citation
DOI: https://doi.org/10.1007/978-981-19-9338-1_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-9337-4
Online ISBN: 978-981-19-9338-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)