Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

A Deep Learning-Based Method for Overhead Contact System Component Recognition Using Mobile 2D LiDAR.

Sensors (Basel, Switzerland)·2020

Same author

LiDAR Point Cloud Recognition of Overhead Catenary System with Deep Learning.

Sensors (Basel, Switzerland)·2020

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 30, 2025

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

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

Published on: November 30, 2022

LiDAR Point Cloud Recognition and Visualization with Deep Learning for Overhead Contact Inspection.

Xiaohan Tu^1,2, Cheng Xu^1,2, Siping Liu^1,2

¹Key Laboratory for Embedded and Network Computing of Hunan Province, Changsha 410082, China.

Sensors (Basel, Switzerland)

|November 13, 2020

Summary

This summary is machine-generated.

This study introduces RobotNet, a lightweight deep learning model for efficient and accurate recognition of overhead contact (OC) components in high-speed railways using LiDAR data. Optimized for speed on embedded devices, it enhances inspection safety and efficiency.

Keywords:

LiDAR (light detection and ranging)convolutional neural networks (CNNs)deep learning overhead contact components point cloud recognition

More Related Videos

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

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

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

Related Experiment Videos

Last Updated: Nov 30, 2025

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

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

Published on: November 30, 2022

Photorealistic Learned Landscapes for Augmented Reality

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

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

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

Area of Science:

Engineering
Computer Science
Artificial Intelligence

Background:

Overhead contact (OC) systems are crucial for high-speed railway power supply.
Manual inspection of OC components is inefficient, inaccurate, and unsafe.
Existing LiDAR point cloud segmentation and recognition methods for OC components face challenges in efficiency, accuracy, and computational complexity.

Purpose of the Study:

To develop a lightweight and efficient deep learning model for recognizing overhead contact (OC) components from LiDAR point cloud data.
To optimize the model for accelerated recognition speed on embedded devices.
To create visualization software for detailed inspection of OC components.

Main Methods:

Proposed RobotNet, a lightweight deep learning model utilizing depthwise and pointwise convolutions and an attention module.
Optimized RobotNet using a compilation tool for enhanced speed on embedded systems.
Developed visualization software for large-scale LiDAR point cloud data and OC component details.

Main Results:

RobotNet achieved higher accuracy and efficiency in recognizing OC components compared to existing methods.
The optimized RobotNet demonstrated an order of magnitude increase in inference speed.
RobotNet exhibited lower computational complexity than other deep learning approaches.
The visualization software effectively displayed complex point cloud data and OC component details.

Conclusions:

RobotNet offers an effective and efficient solution for automated inspection of overhead contact components in high-speed railways.
The model's lightweight design and optimization enable practical deployment on embedded devices for real-time analysis.
The developed visualization tool aids in detailed analysis and understanding of inspection data.