Home Journals Articles Updates About
CN
image
收藏切换
LiDAR-Based 3D Object Detection Algorithm Based on Improved PointPillars
收藏切换
Lie Guo1, 2, Liang Huang1, Yibing Zhao1
Automobile Technology | 2026, (2) : 32 - 38
Less
收藏切换
Automobile Technology | 2026, (2): 32-38
• Special Topic on LiDAR Perception and Multimodal 3D Object Detection Technology for Autonomous Driving •
LiDAR-Based 3D Object Detection Algorithm Based on Improved PointPillars
Full
Lie Guo1, 2, Liang Huang1, Yibing Zhao1
Affiliations
  • 1.School of Mechanical Engineering, Dalian University of Technology, Dalian 116024
  • 2.Ningbo Institute of Dalian University of Technology, Ningbo 315016
Published: 2026-02-24 doi: 10.19620/j.cnki.1000-3703.20240211
Outline
收藏切换

To avoid the missing detection phenomenon caused by loss of local features due to the occlusion and truncation under complex traffic scenes, a LiDAR-based 3D object detection algorithm based on an improved PointPillars framework is proposed. First, the point cloud feature encoding network in PointPillars is enhanced to better preserve important structural information and the relationships within the point cloud data. Then, multi-scale point cloud features are extracted and aggregated through stacked sparse convolution modules and submanifold convolution modules. On the bird's-eye-view feature map that fuses these multi-scale features, 3D bounding boxes of objects are classified and regressed, improving the network's operational efficiency. Finally, experimental tests are conducted on the KITTI dataset. The results show that compared to the traditional PointPillars algorithm, the proposed 3D object detection method improves the Average Precision (AP) of 3D detection for challenging vehicle samples by 6.02 percentage points, and increases the AP for simple pedestrian and cyclist samples in the bird's-eye view by 3.35 and 3.18 percentage points respectively, effectively enhancing 3D object detection accuracy.

LiDAR  /  3D object detection  /  Pillar features  /  Sparse convolution
郭烈, 黄亮, 赵一兵. 基于改进PointPillars的激光雷达三维目标检测算法. 汽车技术, 2026 , (2) : 32 -38 . DOI: 10.19620/j.cnki.1000-3703.20240211
Lie Guo, Liang Huang, Yibing Zhao. LiDAR-Based 3D Object Detection Algorithm Based on Improved PointPillars[J]. Automobile Technology, 2026 , (2) : 32 -38 . DOI: 10.19620/j.cnki.1000-3703.20240211
Appendix
Less
Year 2026 volume Issue 2
161
32
Cite this Article
BibTeX
Article Info
doi: 10.19620/j.cnki.1000-3703.20240211
  • Online Date：2026-09-23
  • Published：2026-02-24
Article Data
Affiliations
History
  • Revised：2025-10-09
Funding
Affiliations
    1.School of Mechanical Engineering, Dalian University of Technology, Dalian 116024
    2.Ningbo Institute of Dalian University of Technology, Ningbo 315016
References
Share
https://castjournals.cast.org.cn/joweb/qcjs/EN/10.19620/j.cnki.1000-3703.20240211
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House