Point-Rich: Enriching Sparse Light Detection and Ranging Point Clouds for Accurate Three-Dimensional Object Detection

Yanchao Zhang, Yinuo Zheng, Dingkun Zhu (), Qiaoyun Wu, Hansheng Zeng, Lipeng Gu and Xiangping Bryce Zhai
Additional contact information
Yanchao Zhang: Special Equipment Safety Supervision Inspection Institute of Jiangsu Province, Nanjing 210036, China
Yinuo Zheng: School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, China
Dingkun Zhu: School of Computer Engineering, Jiangsu University of Technology, Changzhou 213001, China
Qiaoyun Wu: School of Artificial Intelligence, Anhui University, Hefei 230601, China
Hansheng Zeng: Special Equipment Safety Supervision Inspection Institute of Jiangsu Province, Nanjing 210036, China
Lipeng Gu: School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, China
Xiangping Bryce Zhai: School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, China

Mathematics, 2023, vol. 11, issue 23, 1-11

Abstract: LiDAR point clouds often suffer from sparsity and uneven distributions in outdoor scenes, leading to the poor performance of cutting-edge 3D object detectors. In this paper, we propose Point-Rich, which is designed to improve the performance of 3D object detection. Point-Rich consists of two key modules: HighDensity and HighLight. The HighDensity module addresses the issue of density imbalance by enhancing the point cloud density. The HighLight module leverages image semantic features to enrich the point clouds. Importantly, Point-Rich imposes no restrictions on the 3D object detection architecture and remains unaffected by feature or depth blur. The experimental results show that compared with the Pointpillars on the KITTI dataset, the mAP of Point-Rich under the bird’s eyes view improves by 5.53% on average.

Keywords: Point-Rich; 3D object detection; lightweight network (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/23/4809/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/23/4809/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:23:p:4809-:d:1289837

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().