Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images

The conductors of high-speed railway OCSs (Overhead Contact Systems) are susceptible to conductor galloping due to the impact of natural elements such as strong winds, rain, and snow, resulting in conductor fatigue damage and significantly compromising train operational safety. Consequently, monitor...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaotong Yao, Huayu Yuan, Shanpeng Zhao, Wei Tian, Dongzhao Han, Xiaoping Li, Feng Wang, Sihua Wang
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4714
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770523429437440
author Xiaotong Yao
Huayu Yuan
Shanpeng Zhao
Wei Tian
Dongzhao Han
Xiaoping Li
Feng Wang
Sihua Wang
author_facet Xiaotong Yao
Huayu Yuan
Shanpeng Zhao
Wei Tian
Dongzhao Han
Xiaoping Li
Feng Wang
Sihua Wang
author_sort Xiaotong Yao
collection DOAJ
description The conductors of high-speed railway OCSs (Overhead Contact Systems) are susceptible to conductor galloping due to the impact of natural elements such as strong winds, rain, and snow, resulting in conductor fatigue damage and significantly compromising train operational safety. Consequently, monitoring the galloping status of conductors is crucial, and instance segmentation techniques, by delineating the pixel-level contours of each conductor, can significantly aid in the identification and study of galloping phenomena. This work expands upon the YOLO11-seg model and introduces an instance segmentation approach for galloping video and image sensor data of OCS conductors. The algorithm, designed for the stripe-like distribution of OCS conductors in the data, employs four-direction Sobel filters to extract edge features in horizontal, vertical, and diagonal orientations. These features are subsequently integrated with the original convolutional branch to form the FDSE (Four Direction Sobel Enhancement) module. It integrates the ECA (Efficient Channel Attention) mechanism for the adaptive augmentation of conductor characteristics and utilizes the FL (Focal Loss) function to mitigate the class-imbalance issue between positive and negative samples, hence enhancing the model’s sensitivity to conductors. Consequently, segmentation outcomes from neighboring frames are utilized, and mask-difference analysis is performed to autonomously detect conductor galloping locations, emphasizing their contours for the clear depiction of galloping characteristics. Experimental results demonstrate that the enhanced YOLO11-seg model achieves 85.38% precision, 77.30% recall, 84.25% AP@0.5, 81.14% F1-score, and a real-time processing speed of 44.78 FPS. When combined with the galloping visualization module, it can issue real-time alerts of conductor galloping anomalies, providing robust technical support for railway OCS safety monitoring.
format Article
id doaj-art-924b14bdf7df45f3a41110532135aa2d
institution DOAJ
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-924b14bdf7df45f3a41110532135aa2d2025-08-20T03:02:58ZengMDPI AGSensors1424-82202025-07-012515471410.3390/s25154714Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video ImagesXiaotong Yao0Huayu Yuan1Shanpeng Zhao2Wei Tian3Dongzhao Han4Xiaoping Li5Feng Wang6Sihua Wang7School of Electronic & Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, ChinaSchool of Electronic & Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, ChinaSchool of Automatic & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, ChinaChina Railway Beijing Group Co., Ltd., Beijing 100038, ChinaChina Railway Beijing Group Co., Ltd., Beijing 100038, ChinaSchool of Automatic & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, ChinaSchool of Automatic & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, ChinaSchool of Automatic & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, ChinaThe conductors of high-speed railway OCSs (Overhead Contact Systems) are susceptible to conductor galloping due to the impact of natural elements such as strong winds, rain, and snow, resulting in conductor fatigue damage and significantly compromising train operational safety. Consequently, monitoring the galloping status of conductors is crucial, and instance segmentation techniques, by delineating the pixel-level contours of each conductor, can significantly aid in the identification and study of galloping phenomena. This work expands upon the YOLO11-seg model and introduces an instance segmentation approach for galloping video and image sensor data of OCS conductors. The algorithm, designed for the stripe-like distribution of OCS conductors in the data, employs four-direction Sobel filters to extract edge features in horizontal, vertical, and diagonal orientations. These features are subsequently integrated with the original convolutional branch to form the FDSE (Four Direction Sobel Enhancement) module. It integrates the ECA (Efficient Channel Attention) mechanism for the adaptive augmentation of conductor characteristics and utilizes the FL (Focal Loss) function to mitigate the class-imbalance issue between positive and negative samples, hence enhancing the model’s sensitivity to conductors. Consequently, segmentation outcomes from neighboring frames are utilized, and mask-difference analysis is performed to autonomously detect conductor galloping locations, emphasizing their contours for the clear depiction of galloping characteristics. Experimental results demonstrate that the enhanced YOLO11-seg model achieves 85.38% precision, 77.30% recall, 84.25% AP@0.5, 81.14% F1-score, and a real-time processing speed of 44.78 FPS. When combined with the galloping visualization module, it can issue real-time alerts of conductor galloping anomalies, providing robust technical support for railway OCS safety monitoring.https://www.mdpi.com/1424-8220/25/15/4714high-speed railway OCSdeep learningconductor galloping monitoringYOLO11instance segmentation
spellingShingle Xiaotong Yao
Huayu Yuan
Shanpeng Zhao
Wei Tian
Dongzhao Han
Xiaoping Li
Feng Wang
Sihua Wang
Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images
Sensors
high-speed railway OCS
deep learning
conductor galloping monitoring
YOLO11
instance segmentation
title Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images
title_full Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images
title_fullStr Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images
title_full_unstemmed Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images
title_short Deep Learning-Based Instance Segmentation of Galloping High-Speed Railway Overhead Contact System Conductors in Video Images
title_sort deep learning based instance segmentation of galloping high speed railway overhead contact system conductors in video images
topic high-speed railway OCS
deep learning
conductor galloping monitoring
YOLO11
instance segmentation
url https://www.mdpi.com/1424-8220/25/15/4714
work_keys_str_mv AT xiaotongyao deeplearningbasedinstancesegmentationofgallopinghighspeedrailwayoverheadcontactsystemconductorsinvideoimages
AT huayuyuan deeplearningbasedinstancesegmentationofgallopinghighspeedrailwayoverheadcontactsystemconductorsinvideoimages
AT shanpengzhao deeplearningbasedinstancesegmentationofgallopinghighspeedrailwayoverheadcontactsystemconductorsinvideoimages
AT weitian deeplearningbasedinstancesegmentationofgallopinghighspeedrailwayoverheadcontactsystemconductorsinvideoimages
AT dongzhaohan deeplearningbasedinstancesegmentationofgallopinghighspeedrailwayoverheadcontactsystemconductorsinvideoimages
AT xiaopingli deeplearningbasedinstancesegmentationofgallopinghighspeedrailwayoverheadcontactsystemconductorsinvideoimages
AT fengwang deeplearningbasedinstancesegmentationofgallopinghighspeedrailwayoverheadcontactsystemconductorsinvideoimages
AT sihuawang deeplearningbasedinstancesegmentationofgallopinghighspeedrailwayoverheadcontactsystemconductorsinvideoimages