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

Ultra-compact, high-Q silicon microdisk reflectors.

Optics express·2012

Same author

Refractive stability after phaco-DSAEK.

Ophthalmology·2012

Same author

Parathyroid hormone-related protein activates Wnt signaling to specify the embryonic mammary mesenchyme.

Development (Cambridge, England)·2012

Same author

Synthesis of a precursor tripeptide Z-Asp-Val-Tyr-OH of thymopentin by chemo-enzymatic method.

Preparative biochemistry & biotechnology·2012

Same author

The calcineurin-NFAT pathway allows for urokinase receptor-mediated beta3 integrin signaling to cause podocyte injury.

Journal of molecular medicine (Berlin, Germany)·2012

Same author

Giant spinal cord ependymoma with CSF spread.

Neurology·2012

Search research articles

Related Experiment Video

Updated: Jul 23, 2025

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images

Published on: August 31, 2022

Image-Processing-Based Subway Tunnel Crack Detection System.

Xiaofeng Liu¹, Zenglin Hong^1,2, Wei Shi^3,4

¹School of Land Engineering, Chang'an University, Xi'an 710054, China.

Sensors (Basel, Switzerland)

|July 14, 2023

Summary

Tunnel crack detection is crucial for infrastructure safety. A new deep learning method using image processing and a deep convolutional network (Alexnet) significantly improves crack identification accuracy in subway tunnels, enhancing maintenance and preventing accidents.

Keywords:

Alexnet algorithm crack detection image processing subway tunnel

More Related Videos

Mechanoluminescent Visualization of Crack Propagation for Joint Evaluation

Mechanoluminescent Visualization of Crack Propagation for Joint Evaluation

Published on: January 6, 2023

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

Related Experiment Videos

Last Updated: Jul 23, 2025

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images

Published on: August 31, 2022

Mechanoluminescent Visualization of Crack Propagation for Joint Evaluation

Mechanoluminescent Visualization of Crack Propagation for Joint Evaluation

Published on: January 6, 2023

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

Area of Science:

Civil Engineering
Computer Science
Artificial Intelligence

Background:

Urban rail transit construction is increasing, leading to more tunnel diseases.
Cracks are a primary concern in tunnel maintenance, impacting service life and safety.
Timely and efficient crack detection is essential for tunnel management.

Purpose of the Study:

To analyze the design and structure of a tunnel crack detection system.
To propose a novel method for crack identification and feature detection using image processing and deep learning.
To evaluate the effectiveness of a deep convolutional network for detecting cracks in complex tunnel images.

Main Methods:

Image processing techniques were applied to analyze tunnel images.
A deep convolutional network, specifically the Single-Shot MultiBox Detector (SSD) architecture, was developed for object detection.
The proposed method integrated image characteristics with deep learning models.
Support Vector Machine (SVM) and Alexnet deep convolutional neural network were used for comparative analysis.

Main Results:

The Alexnet deep convolutional neural network achieved high accuracy, with test set accuracy reaching 96.7% and training set accuracy reaching 97.5%.
In comparison, the Support Vector Machine (SVM) achieved test set accuracy of 88% and training set accuracy of 87.8%.
The deep convolutional network demonstrated superior performance in crack detection compared to SVM.

Conclusions:

The proposed deep learning-based algorithm, utilizing image processing and a deep convolutional network, is highly effective for detecting cracks in subway tunnels.
This advanced method offers improved accuracy and suitability for complex tunnel environments.
The findings support the adoption of deep learning for enhanced tunnel maintenance and safety.