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

[Effects of elevated atmospheric CO2 on paddy soil nitrogen content during rice season].

Ying yong sheng tai xue bao = The journal of applied ecologyĀ·2010
Same author

Preliminary proposal for surgical classification of sacral tumors.

Journal of neurosurgery. SpineĀ·2010
Same author

Evaluation of Psn, HmuR and a modified LcrV protein delivered to mice by live attenuated Salmonella as a vaccine against bubonic and pneumonic Yersinia pestis challenge.

VaccineĀ·2010
Same author

Microprinting of liver micro-organ for drug metabolism study.

Methods in molecular biology (Clifton, N.J.)Ā·2010
Same author

Eicosapentaenoic acid disrupts the balance between Tregs and IL-17+ T cells through PPARĪ³ nuclear receptor activation and protects cardiac allografts.

The Journal of surgical researchĀ·2010
Same author

[Progress in the study of heat shock protein 90 inhibitors].

Yao xue xue bao = Acta pharmaceutica SinicaĀ·2010

Related Experiment Video

Updated: May 10, 2025

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
12:45

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

Published on: August 31, 2022

2.7K

A Tunnel Crack Segmentation and Recognition Algorithm Using SPGD-and-Generative Adversarial Network Fusion.

Wei Sun1,2, Xiaohu Liu3, Zhiyong Lei1,4

  • 1School of Mechatronic Engineering, Xi'an Technological University, Xi'an 710021, China.

Sensors (Basel, Switzerland)
|April 26, 2025
PubMed
Summary

This study introduces a new tunnel crack segmentation algorithm for UAVs, fusing the Stochastic Parallel Gradient Descent (SPGD) algorithm with a generative adversarial network (GAN). This method significantly enhances crack recognition rates, particularly for small cracks.

Keywords:
generation adversarial network (GAN)image segmentationstochastic parallel gradient descent (SPGD)tunnel crack

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

319
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

2.6K

Related Experiment Videos

Last Updated: May 10, 2025

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
12:45

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

Published on: August 31, 2022

2.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

319
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

2.6K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Civil Engineering

Background:

  • Tunnel crack detection is crucial for infrastructure safety.
  • Existing vision-based systems on UAVs face challenges in accurately recognizing small or textured cracks.
  • Automated and precise crack segmentation is needed to improve inspection efficiency.

Purpose of the Study:

  • To develop an advanced tunnel crack segmentation algorithm for UAV vision systems.
  • To enhance the recognition accuracy and detail extraction of tunnel cracks.
  • To improve the detection rate of small and textured tunnel cracks.

Main Methods:

  • A novel algorithm fusing the Stochastic Parallel Gradient Descent (SPGD) algorithm with a generative adversarial network (GAN).
  • SPGD algorithm is used to enhance image detail and edge information.
  • A GAN comprising an improved U-Net generator and a full convolutional network (FCN) discriminator for segmentation.

Main Results:

  • The proposed algorithm significantly improves the clarity and detail of tunnel crack images.
  • Effective segmentation of tunnel cracks, especially small ones with complex textures, was achieved.
  • Experimental validation on 12 typical tunnel crack images demonstrated a substantial increase in the recognition rate compared to other methods.

Conclusions:

  • The SPGD-and-GAN fusion algorithm offers a superior approach for UAV-based tunnel crack recognition.
  • The enhanced detail and segmentation capabilities address limitations in detecting small and textured cracks.
  • This method holds promise for improving the safety and maintenance of tunnel infrastructure.