Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Comparison of lung scintigraphy with multi-slice spiral computed tomography in the diagnosis of pulmonary embolism.

Clinical nuclear medicine·2009
Same author

[Analysis on the characters of injuries in body surface and deduction of injury-causing instruments in 146 cases].

Fa yi xue za zhi·2009
Same author

Impact of ketone and amino on the inner shell of guanine.

Journal of synchrotron radiation·2009
Same author

Actin turnover is required for myosin-dependent mitochondrial movements in Arabidopsis root hairs.

PloS one·2009
Same author

Direct observation of a widely tunable bandgap in bilayer graphene.

Nature·2009
Same author

Investigation of second-order nonlinearity in poled-polymer during photobleaching.

Optics express·2009

Related Experiment Video

Updated: Sep 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K

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

Xiaotong Yao1, Huayu Yuan1, Shanpeng Zhao2

  • 1School of Electronic & Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China.

Sensors (Basel, Switzerland)
|August 14, 2025
PubMed
Summary

Conductor galloping in high-speed railway overhead contact systems (OCS) poses safety risks. This study enhances YOLOv11-seg for precise galloping detection, improving railway safety monitoring.

Keywords:
YOLO11conductor galloping monitoringdeep learninghigh-speed railway OCSinstance segmentation

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.3K

Related Experiment Videos

Last Updated: Sep 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.3K

Area of Science:

  • Railway Engineering
  • Computer Vision
  • Signal Processing

Background:

  • Overhead Contact Systems (OCS) conductors are vulnerable to galloping caused by natural elements, leading to fatigue damage and safety concerns.
  • Instance segmentation offers a precise method for identifying and analyzing conductor galloping by delineating pixel-level contours.

Purpose of the Study:

  • To develop and evaluate an enhanced instance segmentation model for detecting conductor galloping in OCS.
  • To improve the accuracy and real-time detection capabilities for OCS conductor galloping.

Main Methods:

  • An enhanced YOLOv11-seg model incorporating a Four Direction Sobel Enhancement (FDSE) module with Efficient Channel Attention (ECA) and Focal Loss (FL).
  • Utilized four-direction Sobel filters for edge feature extraction and mask-difference analysis on sequential video frames for autonomous galloping detection.

Main Results:

  • The enhanced model achieved 85.38% precision, 77.30% recall, 84.25% AP@0.5, and an 81.14% F1-score.
  • Real-time processing speed of 44.78 FPS was attained, enabling immediate anomaly alerts.

Conclusions:

  • The proposed instance segmentation approach effectively detects and visualizes conductor galloping in OCS.
  • This method provides robust technical support for enhancing the operational safety of high-speed railway systems.