skip to main content
10.1145/3674225.3674250acmotherconferencesArticle/Chapter ViewAbstractPublication PagespeaiConference Proceedingsconference-collections
research-article

Research on transmission line point cloud classification based on improved PointNet++

Published: 31 July 2024 Publication History

Abstract

Due to the complexity of physical elements in the transmission channel, an improved PointNet++ point cloud classification method for transmission lines is proposed to realize point cloud classification of ground, tower, power line and vegetation, aiming at the problem that the accuracy of point cloud extraction of existing transmission lines is not high and cannot meet the requirements of UAV autonomous fine inspection. Gradient Attention Module (GAM) and Point Attention Module (PAM) are introduced into the point cloud feature extraction layer of PointNet++ to bring fine-grained geometric information to the local feature aggregation process. Further improve the ability of the model to extract point cloud features, so that the model can be better classified. In order to verify the effectiveness of the proposed method, experiments are carried out on the self-made point cloud data set of transmission lines. The experimental results show that the average F1 value of the improved algorithm is 90.39%, which is 3.66 percentage points higher than that of the classic PointNet++.

References

[1]
Yu S, Pingfan N, Pingjuan N, Review on mounted UAV for transmission line inspection[J]. Power System Technology, 2020: 1-15.
[2]
Li W, Luo Z, Xiao Z, A GCN-based method for extracting power lines and pylons from airborne LiDAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 1-14.
[3]
Wang W, Li L. Review of deep learning in point cloud classification[J]. Comput. Eng. Appl, 2022, 58: 26-40.
[4]
Guo Y, Wang H, Hu Q, Deep learning for 3d point clouds: A survey[J]. IEEE transactions on pattern analysis and machine intelligence, 2020, 43(12): 4338-4364.
[5]
Liu Y, Aleksandrov M, Zlatanova S, Classification of power facility point clouds from unmanned aerial vehicles based on adaboost and topological constraints[J]. Sensors, 2019, 19(21): 4717.
[6]
Qi C R, Yi L, Su H, Pointnet++: Deep hierarchical feature learning on point sets in a metric space[J]. Advances in neural information processing systems, 2017, 30.
[7]
Eldar Y, Lindenbaum M, Porat M, The farthest point strategy for progressive image sampling[J]. IEEE Transactions on Image Processing, 1997, 6(9): 1305-1315.
[8]
Hu H, Wang F, Su J, GAM: Gradient Attention Module of Optimization for Point Clouds Analysis[J]. arXiv preprint arXiv:2303.10543, 2023.
[9]
Chen L, Chen W, Xu Z, DAPnet: A double self-attention convolutional network for point cloud semantic labeling[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 9680-9691.

Index Terms

  1. Research on transmission line point cloud classification based on improved PointNet++

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    PEAI '24: Proceedings of the 2024 International Conference on Power Electronics and Artificial Intelligence
    January 2024
    969 pages
    ISBN:9798400716638
    DOI:10.1145/3674225
    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: 31 July 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    PEAI 2024

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 24
      Total Downloads
    • Downloads (Last 12 months)24
    • Downloads (Last 6 weeks)4
    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