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 Gene Feature Based on Histone Modifications Can Predict the Prognosis of Prostate Cancer.

Biomedicines·2026

Same author

Efficacy and safety of infigratinib in patients with refractory advanced gastric or gastroesophageal junction adenocarcinoma harboring FGFR2 gene amplification: a single-arm, multicenter phase 2 trial.

British journal of cancer·2026

Same author

Integrated transcriptome and metabolome reveal <i>Mycoplasma hyopneumoniae</i> -induced lipid accumulation, inflammation, oxidative stress, and energy imbalance in the liver of pigs.

Virulence·2026

Same author

Development of a High-Efficiency Hairy Root Transformation System for Diverse Cowpea (<i>Vigna unguiculata</i>) Genotypes.

Plants (Basel, Switzerland)·2026

Same author

Association of systemic immune-inflammation index with all-cause mortality in lung cancer patients undergoing radiotherapy: a retrospective cohort study.

Frontiers in oncology·2026

Same author

Self-adaptive cleaning technology for artillery laser ignition windows based on current feedback.

Scientific reports·2026

Same journal

Research on a Regional Availability Evaluation Model for Road-Area High-Entropy Energy Based on Synergy Factors.

Entropy (Basel, Switzerland)·2026

Same journal

Atmospheric Turbulence Channel Modeling and Performance Analysis of a CO-ZP-OFDM Coherent Optical Communication System for UAV Air-to-Ground Scenarios.

Entropy (Basel, Switzerland)·2026

Same journal

Information Geometry and Asymptotic Theory for SMML Estimators.

Entropy (Basel, Switzerland)·2026

Same journal

Correlation Entropy and Power-Law Kinetics.

Entropy (Basel, Switzerland)·2026

Same journal

Research on the Contagion of Systemic Financial Risk Under the Impact of Climate Risks-From the Perspective of Complex Networks and Machine Learning.

Entropy (Basel, Switzerland)·2026

Same journal

The Statistical-Mechanical Meaning of the Wave Function of Quantum Mechanics.

Entropy (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 12, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

A Study on Railway Surface Defects Detection Based on Machine Vision.

Tangbo Bai^1,2, Jialin Gao^1,2, Jianwei Yang^1,2

¹School of Mechanical-Electronic and Vehicle Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China.

Entropy (Basel, Switzerland)

|November 27, 2021

Summary

This summary is machine-generated.

This study introduces an improved YOLOv4 model for detecting rail surface defects, significantly reducing model size and increasing speed. The enhanced method ensures faster and more accurate railway defect detection for safe transit operations.

Keywords:

MobileNetV3 YOLOv4 deep learning machine vision rail surface defect detection

More Related Videos

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Related Experiment Videos

Last Updated: Oct 12, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

Area of Science:

Railway engineering
Computer vision
Artificial intelligence

Background:

Rail surface defect detection is crucial for safe rail transit operations.
Traditional machine vision methods struggle with diverse and small defect features.
Existing deep learning models are often large, slow, and inaccurate.

Purpose of the Study:

To propose a lightweight and efficient deep learning model for railway surface defect detection.
To improve the accuracy and speed of detecting diverse rail surface defects.
To address the limitations of existing methods in terms of model size, parameters, and detection speed.

Main Methods:

An improved YOLOv4 (You Only Look Once) model was developed for railway surface defect detection.
MobileNetv3 was integrated as the backbone network for feature extraction.
Deep separable convolution was applied to the PANet layer to optimize the network.

Main Results:

The proposed method significantly reduced model parameters by 78.04%.
Detection speed increased by 10.36 frames per second compared to standard YOLOv4.
Model volume decreased by 78%, demonstrating a lightweight network.
Achieved higher detection accuracy than other existing methods.

Conclusions:

The improved YOLOv4 model offers a lightweight and efficient solution for railway surface defect detection.
The method enables fast and accurate detection, suitable for real-time applications.
This approach enhances the safety and reliability of rail transit systems.