Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion

Power line segmentation plays a critical role in ensuring the safety of transmission line UAV inspection flights. To address the challenges of small target scale, complex backgrounds, and excessive model parameters in existing deep learning-based power line segmentation algorithms, this paper introd...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenqiang Zhu, Huarong Ding, Gujing Han, Wei Wang, Minlong Li, Liang Qin
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3551
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722232961499136
author Wenqiang Zhu
Huarong Ding
Gujing Han
Wei Wang
Minlong Li
Liang Qin
author_facet Wenqiang Zhu
Huarong Ding
Gujing Han
Wei Wang
Minlong Li
Liang Qin
author_sort Wenqiang Zhu
collection DOAJ
description Power line segmentation plays a critical role in ensuring the safety of transmission line UAV inspection flights. To address the challenges of small target scale, complex backgrounds, and excessive model parameters in existing deep learning-based power line segmentation algorithms, this paper introduces RGS-UNet, a lightweight segmentation model integrating a residual-like cross-layer feature fusion module. First, ResNet18 is adopted to reconstruct a UNet backbone network as an encoder module to enhance the network’s feature extraction capability for small targets. Second, ordinary convolution in the residual block of ResNet18 is optimized by introducing the Ghost Module, which significantly reduces the computational load of the model’s backbone network. Third, a residual-like addition method is designed to embed the SIMAM attention mechanism module into both encoder and decoder stages, which improves the model’s ability to extract power lines from complex backgrounds. Finally, the Mish activation function is applied in deep convolutional layers to maintain feature extraction accuracy and mitigate overfitting. Experimental results demonstrate that compared with classical UNet, the optimized network achieves 2.05% and 2.58% improvements in F1-Score and IoU, respectively, while reducing the parameter count to 57.25% of the original model. The algorithm achieves better performance improvements in both accuracy and lightweighting, making it suitable for edge-side deployment.
format Article
id doaj-art-2755d7e9175642ccbfcbdfa0e3d16516
institution DOAJ
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-2755d7e9175642ccbfcbdfa0e3d165162025-08-20T03:11:24ZengMDPI AGSensors1424-82202025-06-012511355110.3390/s25113551Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature FusionWenqiang Zhu0Huarong Ding1Gujing Han2Wei Wang3Minlong Li4Liang Qin5School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, ChinaSchool of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, ChinaSchool of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, ChinaSchool of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, ChinaSchool of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaPower line segmentation plays a critical role in ensuring the safety of transmission line UAV inspection flights. To address the challenges of small target scale, complex backgrounds, and excessive model parameters in existing deep learning-based power line segmentation algorithms, this paper introduces RGS-UNet, a lightweight segmentation model integrating a residual-like cross-layer feature fusion module. First, ResNet18 is adopted to reconstruct a UNet backbone network as an encoder module to enhance the network’s feature extraction capability for small targets. Second, ordinary convolution in the residual block of ResNet18 is optimized by introducing the Ghost Module, which significantly reduces the computational load of the model’s backbone network. Third, a residual-like addition method is designed to embed the SIMAM attention mechanism module into both encoder and decoder stages, which improves the model’s ability to extract power lines from complex backgrounds. Finally, the Mish activation function is applied in deep convolutional layers to maintain feature extraction accuracy and mitigate overfitting. Experimental results demonstrate that compared with classical UNet, the optimized network achieves 2.05% and 2.58% improvements in F1-Score and IoU, respectively, while reducing the parameter count to 57.25% of the original model. The algorithm achieves better performance improvements in both accuracy and lightweighting, making it suitable for edge-side deployment.https://www.mdpi.com/1424-8220/25/11/3551power line segmentationlightweight UNetGhost Moduleclass residual addition
spellingShingle Wenqiang Zhu
Huarong Ding
Gujing Han
Wei Wang
Minlong Li
Liang Qin
Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion
Sensors
power line segmentation
lightweight UNet
Ghost Module
class residual addition
title Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion
title_full Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion
title_fullStr Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion
title_full_unstemmed Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion
title_short Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion
title_sort power line segmentation algorithm based on lightweight network and residue like cross layer feature fusion
topic power line segmentation
lightweight UNet
Ghost Module
class residual addition
url https://www.mdpi.com/1424-8220/25/11/3551
work_keys_str_mv AT wenqiangzhu powerlinesegmentationalgorithmbasedonlightweightnetworkandresiduelikecrosslayerfeaturefusion
AT huarongding powerlinesegmentationalgorithmbasedonlightweightnetworkandresiduelikecrosslayerfeaturefusion
AT gujinghan powerlinesegmentationalgorithmbasedonlightweightnetworkandresiduelikecrosslayerfeaturefusion
AT weiwang powerlinesegmentationalgorithmbasedonlightweightnetworkandresiduelikecrosslayerfeaturefusion
AT minlongli powerlinesegmentationalgorithmbasedonlightweightnetworkandresiduelikecrosslayerfeaturefusion
AT liangqin powerlinesegmentationalgorithmbasedonlightweightnetworkandresiduelikecrosslayerfeaturefusion