Laser & Infrared, Volume. 54, Issue 2, 222(2024)

A point cloud segmentation method based on position encoding and Dual-distance Attention

WEN Zhi-cheng, WANG Lei*, FENG Jin-liang, and YE Sen-hui
Author Affiliations
  • School of Information Engineering, East China University of Technology, Nanchang 330013, China
  • show less

    In recent years, convolution and graph operations have been widely used in research to capture feature information from point clouds, leading to good performance in semantic segmentation tasks. However, these methods have limitations in representing local information of point clouds, and a significant amount of feature information is lost by employing symmetric pooling operations. To address these issues, the DualRes-Net network is proposed. The network incorporates a Position Encoding Module to encode local coordinate features, enabling the network to focus on point cloud position information and obtain better local feature representations. And differences between center and neighboring points are combined with attention using a Dual-distance Attention Pooling, enhancing the adaptive aggregation ability of attention pooling for local point cloud information. A De-Differentiation Residual structure is used in each stage of the network to extract deep features of point clouds. Since different input types have significant distribution differences, MLP is applied to each type of feature separately to stabilize model training and improve model performance. Finally, in the semantic segmentation experiments in S3DIS Area5, the semantic segmentation performance of the proposed method achieves a mIoU of 63.7%, surpassing many existing networks, and demonstrating the effectiveness of the method.

    Tools

    Get Citation

    Copy Citation Text

    WEN Zhi-cheng, WANG Lei, FENG Jin-liang, YE Sen-hui. A point cloud segmentation method based on position encoding and Dual-distance Attention[J]. Laser & Infrared, 2024, 54(2): 222

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: May. 11, 2023

    Accepted: Jun. 4, 2025

    Published Online: Jun. 4, 2025

    The Author Email: WANG Lei (wlei598@163.com)

    DOI:10.3969/j.issn.1001-5078.2024.02.009

    Topics