SPTM: A Transformer-Mamba Decoder With Superpoint Pooling for Semantic Segmentation of Power Tower Point Clouds

Semantic segmentation of three-dimensional (3D) power tower point clouds is a key technology for smart grid inspection and digital modeling of transmission corridors. However, slender structures such as power lines are sparse and discontinuous, and susceptible to occlusion in uninhabited aerial vehicle (UAV) light detection and ranging (LiDAR) point clouds, resulting in insufficient segmentation precision for existing methods. To address this issue, a novel 3D power tower semantic segmentation method, superpoint transmamba (SPTM), is proposed. Firstly, a sparse 3D U-Net is used as the backbone network, and a superpoint pooling layer is used to aggregate features in locally geometrically consistent regions. Then, a hybrid query decoder that fuses the Transformer and the Mamba state-space model is introduced in the decoding stage to balance local geometric details with the modeling of global long-range dependencies. Finally, a series of experiments are conducted on a dataset of power tower point clouds collected by UAVs to validate the effectiveness of the proposed method. Experiments demonstrate that SPTM outperforms existing mainstream methods (such as Point Transformer, Stratified Transformer, and 3DSwin Transformer) in metrics such as mean intersection over union (mIoU) and mean accuracy (mAcc), achieving significant improvements in power line classification. Ablation experiments further validate the complementarity and effectiveness of superpoint pooling and the Mamba module in identifying slender structures. This method provides an efficient and accurate solution for 3D point cloud semantic segmentation in complex power transmission scenarios.

• Publication year

  2026

• Venue

  IEEE Access

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/ACCESS.2025.3649640
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• State-of-the-Art Review on the Application of Unmanned Aerial Vehicles (UAVs) in Power Line Inspections: Current Innovations, Trends, and Future Prospects

  2025cited by this paper
• Semantic Segmentation of Key Categories in Transmission Line Corridor Point Clouds Based on EMAFL-PTv3

  2025cited by this paper
• PointNet++ model based on directional attention for insulators segmentation

  2025cited by this paper
• RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene

  2025cited by this paper
• Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

  2024cited by this paper
• PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders

  2024cited by this paper
• Bilinear Distance Feature Network for Semantic Segmentation in PowerLine Corridor Point Clouds

  2024cited by this paper
• Research on transmission line point cloud classification based on improved PointNet++

  2024cited by this paper
• Insulator Extraction from UAV LiDAR Point Cloud Based on Multi-Type and Multi-Scale Feature Histogram

  2024cited by this paper
• Identification method of insulators in complex overhead transmission line scenarios based on three-dimensional point cloud features

  2024cited by this paper
• PointMamba: A Simple State Space Model for Point Cloud Analysis

  2024cited by this paper
• Power-Line Extraction and Modelling from 3D Point Clouds Data Based on K-D Tree DBSCAN Algorithm

  2023cited by this paper
• Semantic Segmentation of Transmission Corridor 3D Point Clouds Based on CA-PointNet++

  2023cited by this paper
• SS-IPLE: Semantic Segmentation of Electric Power Corridor Scene and Individual Power Line Extraction From UAV-Based Lidar Point Cloud

  2023cited by this paper
• Point Transformer V3: Simpler, Faster, Stronger

  2023cited by this paper
• Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

  2022cited by this paper
• Stratified Transformer for 3D Point Cloud Segmentation

  2022cited by this paper
• Masked-attention Mask Transformer for Universal Image Segmentation

  2021cited by this paper
• Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling

  2021cited by this paper
• Point Transformer

  2020cited by this paper
• RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

  2019cited by this paper
• Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs

  2017cited by this paper
• Focal Loss for Dense Object Detection

  2017cited by this paper
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

  2017cited by this paper
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

  2016cited by this paper

• No citing papers are available for this paper.