Login / Register Submit Your Article
cover
Journal of Globe Scientific Reports

Volume 6, 2024 - Issue 2

Submit Manuscript Journal Homepage
Latest Issue
Input keywords, title, abstract, author, affiliation etc..
Article Menu
Browse this journal
Vol. 7 (2025)
Vol. 6 (2024)
Vol. 5 (2023)
Vol. 4 (2022)
Vol. 3 (2021)
Vol. 2 (2020)
Vol. 1 (2019)
Recommend Papers
Current Challenges and Strategies for EU Immigration Policy
Case Study: Predicting Academic Success in Business English through Learning Behavior and Psychological Support Analysis with Machine Learning
Deep Learning and Computational Mathematics in Crisis Detection for International Students
Utilizing Fuzzy Neural Networks for Accurate English Grade Forecasting
Attention Mechanism-Enhanced Imaging Techniques for Brain Tumor Classification
Journal Article An open access journal
Journal Article

Deep learning-based spatial vector point set partition model

by Yulin Chen 1,# ,  Junwen Chen 2,# ,  Yuhong Xiao 3,# ,  CHENG SUNNY 4,& ,  Muxin Shi 2,&  and  Jiahao Li 2,*
1
University College London, London, United Kingdom
2
Shenzhen Aurora International Academy, Shenzhen, China
3
Shenzhen Senior High School Group International Division, Shenzhen, China
4
The Affiliated International School of Shenzhen University, Shenzhen, China
#
Co-first author
&
Co-second author
*
Author to whom correspondence should be addressed.
JGSR  2024 6(2):100; https://doi.org/10.69610/j.gsr.202407302
Received: 29 June 2024 / Accepted: 20 July 2024 / Published Online: 30 July 2024
View Full-Text
Download PDF

Abstract

In the era of big data, the scale and complexity of spatial data are continuously increasing, making the effective partitioning and classification of spatial vector point sets a critical and challenging problem. This study proposes a spatial vector point set partitioning model based on deep learning, which leverages techniques such as Convolutional Neural Networks (CNN) and PointNet. Through an end-to-end learning process, the model automatically extracts the intrinsic structures and patterns of the data. The method employs 3D-CNN and PointNet models to process point cloud data, achieving efficient and accurate partitioning results. The findings indicate that the model demonstrates stronger robustness and higher accuracy when handling large-scale, high-dimensional data, with a classification accuracy reaching 100%. In conclusion, the spatial vector point set partitioning model based on deep learning holds significant theoretical and practical value, offering more precise and reliable technical support for related fields.

Keywords: Deep learning; point set division; 3D-CNN; Point net; Point net;
Copyright: © 2024 by Chen, Chen, Xiao, SUNNY, Shi and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (Creative Commons Attribution 4.0 International License). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
Show Figures

Share and Cite

ACS Style
Chen, Y.; Chen, J.; Xiao, Y.; SUNNY, C.; Shi, M.; Li, J. Deep learning-based spatial vector point set partition model. Journal of Globe Scientific Reports, 2024, 6, 100. doi:10.69610/j.gsr.202407302
AMA Style
Chen Y, Chen J, Xiao Y et al.. Deep learning-based spatial vector point set partition model. Journal of Globe Scientific Reports; 2024, 6(2):100. doi:10.69610/j.gsr.202407302
Chicago/Turabian Style
Chen, Yulin; Chen, Junwen; Xiao, Yuhong; SUNNY, CHENG; Shi, Muxin; Li, Jiahao 2024. "Deep learning-based spatial vector point set partition model" Journal of Globe Scientific Reports 6, no.2:100. doi:10.69610/j.gsr.202407302

Article Metrics

Article Access Statistics

References

  1. Xi Jun, Duan Yong. 3D point cloud classification based on PointCloudTransformer and optimized Ensemble learning [J/OL]. Journal of electronic measurement and instrument, 1-12 [2024-07-20]. HTTP: / / http://kns.cnki.net/kcms/detail/11.2488.TN.20240624.1433.019.html.
  2. IDA, Zhang Xiaoyang, Xu Ce, et al. New advances in semantic segmentation methods based on large-scale point cloud deep learning [J]. Advances in Laser and Optoelectronics, 2019,61(12):43-60. (in Chinese)
  3. Jia Mingda, Yang Jinming, Meng Weiliang, et al. Research progress of fusion point cloud and image environmental target detection [J]. Journal of Image and Graphics, 2019,29(06):1765-1784. (in Chinese)
  4. Zhang Y Y. Research on point cloud object detection method based on 3D Convolutional neural network [D]. The northern industrial university, 2024. DOI: 10.26926 /, dc nki. Gbfgu. 2024.000121.
  5. Liu Zhaodi. The point cloud target tracking algorithm based on depth of learning research [D]. The northern industrial university, 2024. The DOI: 10.26926 /, dc nki. Gbfgu. 2024.000587.
  6. Chen Shaojin. Research on semantic segmentation of airborne point cloud in deep learning based on geometric features [D]. Disaster prevention institute of science and technology, 2024. DOI: 10.27899 /, dc nki. GFZKJ. 2024.000015.
  7. Lu Bin, Wang Zhiyuan. Combination of super voxel and color information region growing point cloud segmentation method [J]. Computer engineering and design, 2024, (5) : 1482-1489. The DOI: 10.16208 / j.i ssn1000-7024.2024.05.027.
  8. Zhang Dongdong, Guo Jie, Chen Yang. Research on point cloud object recognition based on deep learning and ensemble Learning [J]. Computer and Digital Engineering, 2019,52(03):761-767. (in Chinese)
  9. Guo Dawei, Li Jinghao, Army. 3 d point cloud registration method of multi-scale deep learning [J/OL]. Journal of intelligent systems, 1-10 [2024-07-20]. http://kns.cnki.net/kcms/detail/23.1538.TP.20240313.1451.003.html.
  10. Jiang Peige, Wu Jie, Zhang Sheirong, et al. Segmentation of point cloud based on deep learning and flood risk simulation [J]. Advances in water science, 2024, 35 (01) : 62-73. The DOI: 10.14042 / j.carol carroll nki 32.1309.2024.01.006.
  11. Shu Jun, Li Yiyang, Yang Li, et al. A multi-modal point cloud classification network based on residual MLP [J]. Journal of Chongqing University of Technology (Natural Science), 2019,38(06):242-249. (in Chinese)
  12. Liu Hui, Du Zhipeng, Yang Feng, et al. Real-time target identification method for forest and orchard spray operation based on lightweight PointNet network [J]. Transactions of the Chinese Society of Agricultural Engineering, 2018,40(08):144-151.
  13. Liu Qixin, Lu Jinzheng, Huang Bingsen. Optimization based on feature fusion and loss of semantic segmentation of point cloud network [J]. Computer technology and development, 2024, (5) : 66-72. The DOI: 10.20165 / j.carol carroll nki ISSN1673-629 - x., 2024.0042.
  14. Liang Jietao, Luo Bing, Fu Lanhui, et al. Based on coordinate geometry sampling point cloud registration method [J/OL]. Computer application, 1-11 [2024-07-22]. http://kns.cnki.net/kcms/detail/51.1307.TP.20240423.1134.002.html.
  15. Xu Jie, Liu Hui, Shen Yue, et al. Tree point cloud classification and segmentation in nursery based on improved Pointnet ++ model [J]. Chinese Journal of Lasers, 2019,51(08):193-203.