RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene

The digitization of uninterrupted operation in the distribution network is of great significance for improving people’s quality of life and promoting economic development. As an important means of achieving digitization, point cloud technology is crucial to the intelligent transformation of distribu...

Full description

Saved in:
Bibliographic Details
Main Authors: Deyu Nie, Linong Wang, Shaocheng Wu, Zhenyang Chen, Yongwen Li, Bin Song
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/8/2370
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850180232643870720
author Deyu Nie
Linong Wang
Shaocheng Wu
Zhenyang Chen
Yongwen Li
Bin Song
author_facet Deyu Nie
Linong Wang
Shaocheng Wu
Zhenyang Chen
Yongwen Li
Bin Song
author_sort Deyu Nie
collection DOAJ
description The digitization of uninterrupted operation in the distribution network is of great significance for improving people’s quality of life and promoting economic development. As an important means of achieving digitization, point cloud technology is crucial to the intelligent transformation of distribution network. To this end, the authors embedded the improved RSA (residual spatial attention) module and modified the loss function of network, proposing a deep learning network called RSA-PT for the semantic segmentation of a distribution network scene point cloud. According to the requirements of uninterrupted operation in the distribution network, the authors segmented the point cloud into the following ten classes: high-voltage line, low-voltage line, groundline, tower, ground, road, house, tree, obstacle, and car. Model and attention mechanism comparison experiments, as well as ablation studies, were conducted on the distribution network scene point cloud dataset. The experimental results showed that RSA-PT achieved <i>mIoU</i> (mean intersection over union), <i>mA</i> (mean accuracy), and <i>OA</i> (overall accuracy) indicators of 90.55%, 94.20%, and 97.20%, respectively. Furthermore, the <i>mIoU</i> of RSA-PT exceeded the baseline model by 6.63%. Our work could provide a technical foundation for the digital analysis of conditions for uninterrupted operation in distribution networks.
format Article
id doaj-art-0ac3d2e8e0694e34aef65096e6700932
institution OA Journals
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-0ac3d2e8e0694e34aef65096e67009322025-08-20T02:18:15ZengMDPI AGSensors1424-82202025-04-01258237010.3390/s25082370RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network SceneDeyu Nie0Linong Wang1Shaocheng Wu2Zhenyang Chen3Yongwen Li4Bin Song5Engineering Research Center of Ministry of Education for Lightning Protection and Grounding Technology, School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaEngineering Research Center of Ministry of Education for Lightning Protection and Grounding Technology, School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaEngineering Research Center of Ministry of Education for Lightning Protection and Grounding Technology, School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaEngineering Research Center of Ministry of Education for Lightning Protection and Grounding Technology, School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaEngineering Research Center of Ministry of Education for Lightning Protection and Grounding Technology, School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaEngineering Research Center of Ministry of Education for Lightning Protection and Grounding Technology, School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaThe digitization of uninterrupted operation in the distribution network is of great significance for improving people’s quality of life and promoting economic development. As an important means of achieving digitization, point cloud technology is crucial to the intelligent transformation of distribution network. To this end, the authors embedded the improved RSA (residual spatial attention) module and modified the loss function of network, proposing a deep learning network called RSA-PT for the semantic segmentation of a distribution network scene point cloud. According to the requirements of uninterrupted operation in the distribution network, the authors segmented the point cloud into the following ten classes: high-voltage line, low-voltage line, groundline, tower, ground, road, house, tree, obstacle, and car. Model and attention mechanism comparison experiments, as well as ablation studies, were conducted on the distribution network scene point cloud dataset. The experimental results showed that RSA-PT achieved <i>mIoU</i> (mean intersection over union), <i>mA</i> (mean accuracy), and <i>OA</i> (overall accuracy) indicators of 90.55%, 94.20%, and 97.20%, respectively. Furthermore, the <i>mIoU</i> of RSA-PT exceeded the baseline model by 6.63%. Our work could provide a technical foundation for the digital analysis of conditions for uninterrupted operation in distribution networks.https://www.mdpi.com/1424-8220/25/8/2370point cloudsemantic segmentationdistribution networkuninterrupted operationpoint transformer
spellingShingle Deyu Nie
Linong Wang
Shaocheng Wu
Zhenyang Chen
Yongwen Li
Bin Song
RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene
Sensors
point cloud
semantic segmentation
distribution network
uninterrupted operation
point transformer
title RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene
title_full RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene
title_fullStr RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene
title_full_unstemmed RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene
title_short RSA-PT: A Point Transformer-Based Semantic Segmentation Network for Uninterrupted Operation in a Distribution Network Scene
title_sort rsa pt a point transformer based semantic segmentation network for uninterrupted operation in a distribution network scene
topic point cloud
semantic segmentation
distribution network
uninterrupted operation
point transformer
url https://www.mdpi.com/1424-8220/25/8/2370
work_keys_str_mv AT deyunie rsaptapointtransformerbasedsemanticsegmentationnetworkforuninterruptedoperationinadistributionnetworkscene
AT linongwang rsaptapointtransformerbasedsemanticsegmentationnetworkforuninterruptedoperationinadistributionnetworkscene
AT shaochengwu rsaptapointtransformerbasedsemanticsegmentationnetworkforuninterruptedoperationinadistributionnetworkscene
AT zhenyangchen rsaptapointtransformerbasedsemanticsegmentationnetworkforuninterruptedoperationinadistributionnetworkscene
AT yongwenli rsaptapointtransformerbasedsemanticsegmentationnetworkforuninterruptedoperationinadistributionnetworkscene
AT binsong rsaptapointtransformerbasedsemanticsegmentationnetworkforuninterruptedoperationinadistributionnetworkscene