skip to main content
10.1145/3653781.3653817acmotherconferencesArticle/Chapter ViewAbstractPublication PagescvdlConference Proceedingsconference-collections
research-article

A High Precision Reconstruction Method of Point Cloud for Three-dimensional Radar Imaging

Published: 01 June 2024 Publication History

Abstract

High-resolution 3D radar imaging technology provides rich 3D information on detection targets in all weather conditions, but compared with optical or laser sensors, it is limited by the electromagnetic scattering mechanism and has the problems of sparse target point clouds and incomplete contours, which are disadvantageous for target detection and identification in radar point clouds. To address this problem, a Graphical Convolutional Radar Point Cloud Reconstruction Network (GCPRN) for imaging radar is proposed by combining snowflake deconvolution network and dynamic graphical convolution algorithm in this paper. In this paper, the dynamic graph convolution algorithm is used to improve the feature extraction and inference ability to obtain accurate target contour information; the snowflake deconvolution network is designed to construct the backbone framework of radar point cloud reconstruction to realize the refined point cloud reconstruction. Finally, 20 airborne aircraft models are used for 3D radar imaging simulation and point cloud dataset construction in this paper. The results show that the point cloud reconstruction accuracy of this paper can be improved by 36.4% compared with existing methods such as PU-Net and MPU.

References

[1]
Anthony J Correnti, Gadi Wollstein, Lori Lyn Price, and Joel S Schuman. 2003. Comparison of optic nerve head assessment with a digital stereoscopic camera (discam), scanning laser ophthalmoscopy, and stereophotography. Ophthalmology 110, 8 (2003), 1499–1505.
[2]
David L Donoho. 2006. Compressed sensing. IEEE Transactions on information theory 52, 4 (2006), 1289–1306.
[3]
Hang Du, Xuejun Yan, Jingjing Wang, Di Xie, and Shiliang Pu. 2022. Point cloud upsampling via cascaded refinement network. In Proceedings of the Asian Conference on Computer Vision. 586–601.
[4]
YANG Jianyu. 2019. Multi-directional evolution trend and law analysis of radar ground imaging technology. Journal of Radars 8, 6 (2019), 669–692.
[5]
WU Jin. 2012. Research on synthetic aperture lidar imaging. Journal of Radars 1, 4 (2012), 353–360.
[6]
Ruihui Li, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, and Pheng-Ann Heng. 2019. Pu-gan: a point cloud upsampling adversarial network. In Proceedings of the IEEE/CVF international conference on computer vision. 7203–7212.
[7]
Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger. 2019. Occupancy networks: Learning 3d reconstruction in function space. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 4460–4470.
[8]
Xie Pengfei, Zhang Lei, and Wu Zhenhua. 2018. A Cylindrical Scanning Millimeter-Wave 3D Imaging Algorithm Incorporating ω -K and BP Algorithms. Journal of Radars 7, 3 (2018), 387–394.
[9]
Anh Viet Phan, Minh Le Nguyen, Yen Lam Hoang Nguyen, and Lam Thu Bui. 2018. Dgcnn: A convolutional neural network over large-scale labeled graphs. Neural Networks 108 (2018), 533–543.
[10]
Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 652–660.
[11]
Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30 (2017).
[12]
Guocheng Qian, Abdulellah Abualshour, Guohao Li, Ali Thabet, and Bernard Ghanem. 2021. Pu-gcn: Point cloud upsampling using graph convolutional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11683–11692.
[13]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234–241.
[14]
Manolis Savva, Fisher Yu, Hao Su, M Aono, B Chen, D Cohen-Or, W Deng, Hang Su, Song Bai, Xiang Bai, 2016. Shrec16 track: largescale 3d shape retrieval from shapenet core55. In Proceedings of the eurographics workshop on 3D object retrieval, Vol. 10. 13.
[15]
Wei Shunjun, Tian Bokun, Zhang Xiaoling, Shijun, 2018. A compressed-aware line array 3D SAR self-focusing imaging algorithm based on semi-positive definite planning. Journal of Radars 7, 6 (2018), 664–675.
[16]
Shunjun Wei, Jiadian Liang, Mou Wang, Jun Shi, Xiaoling Zhang, and Jinhe Ran. 2021. AF-AMPNet: A deep learning approach for sparse aperture ISAR imaging and autofocusing. IEEE Transactions on Geoscience and Remote Sensing 60 (2021), 1–14.
[17]
Peng Xiang, Xin Wen, Yu-Shen Liu, Yan-Pei Cao, Pengfei Wan, Wen Zheng, and Zhizhong Han. 2022. Snowflake point deconvolution for point cloud completion and generation with skip-transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 5 (2022), 6320–6338.
[18]
Qiu Xiaolan, Jiao Zekun, Peng Lingxiao, Chen Jiankun, Guo Jiayi, Zhou Liangzhong, Chen Longyong, Ding Chibiao, Xu Feng, Dong Qiulei, 2021. SARMV3D-1.0: SAR Microwave Vision 3D Imaging Dataset. Journal of Radars 10, 4 (2021), 485–498.
[19]
Yaoqing Yang, Chen Feng, Yiru Shen, and Dong Tian. 2018. Foldingnet: Point cloud auto-encoder via deep grid deformation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 206–215.
[20]
Wang Yifan, Shihao Wu, Hui Huang, Daniel Cohen-Or, and Olga Sorkine-Hornung. 2019. Patch-based progressive 3d point set upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5958–5967.
[21]
Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, and Pheng-Ann Heng. 2018. Pu-net: Point cloud upsampling network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2790–2799.
[22]
Wentao Yuan, Tejas Khot, David Held, Christoph Mertz, and Martial Hebert. 2018. Pcn: Point completion network. In 2018 international conference on 3D vision (3DV). IEEE, 728–737.
[23]
Zichen Zhou, Shunjun Wei, Hao Zhang, Rong Shen, Mou Wang, Jun Shi, and Xiaoling Zhang. 2022. SAF-3DNet: Unsupervised AMP-inspired network for 3-D MMW SAR imaging and autofocusing. IEEE Transactions on Geoscience and Remote Sensing 60 (2022), 1–15.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
CVDL '24: Proceedings of the International Conference on Computer Vision and Deep Learning
January 2024
506 pages
ISBN:9798400718199
DOI:10.1145/3653804
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 June 2024

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. 3D Radar Imaging
  2. Deep Learning
  3. Feature Extraction
  4. Graph Convolution
  5. Point Cloud Reconstruction

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

CVDL 2024

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 35
    Total Downloads
  • Downloads (Last 12 months)35
  • Downloads (Last 6 weeks)3
Reflects downloads up to 17 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media