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

Controlling fungal growth and quality deterioration in germ-remaining rice using silkworm pupa chitosan.

Scientific reports·2026
Same author

Utility of extended HPV genotyping in cervical cancer screening: a prospective population-based cohort study in China.

Frontiers in oncology·2026
Same author

Preparation of Gallic Acid-Grafted Silkworm Pupae Chitosan Composite Film and Its Application in Blueberry Preservation.

Foods (Basel, Switzerland)·2025
Same author

Application of chitosan extracted from silkworm pupae by ultrasound-assisted enzymatic method on strawberry preservation.

International journal of biological macromolecules·2025
Same author

N6-Methyladenosine Promotes the Transcription of c-Src Kinase via IRF1 to Facilitate the Proliferation of Liver Cancer.

Oncology research·2025
Same author

Compositional Physical Reasoning of Objects and Events From Videos.

IEEE transactions on pattern analysis and machine intelligence·2025

Related Experiment Video

Updated: Jun 11, 2025

Screening of Coatings for an All-Solid-State Battery Using In Situ Transmission Electron Microscopy
07:20

Screening of Coatings for an All-Solid-State Battery Using In Situ Transmission Electron Microscopy

Published on: January 20, 2023

2.5K

Research on Lightweight Method of Insulator Target Detection Based on Improved SSD.

Bing Zeng1, Yu Zhou1, Dilin He1

  • 1Nanchang Institute of Technology, Nanchang 330099, China.

Sensors (Basel, Switzerland)
|September 28, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a lightweight insulator detection algorithm for edge devices, significantly reducing model size and improving processing speed while maintaining high accuracy. The enhanced algorithm supports efficient edge intelligence applications.

Keywords:
SSDchannel pruninginsulatorlightweighttarget detection

More Related Videos

In Situ SIMS and IR Spectroscopy of Well-defined Surfaces Prepared by Soft Landing of Mass-selected Ions
10:22

In Situ SIMS and IR Spectroscopy of Well-defined Surfaces Prepared by Soft Landing of Mass-selected Ions

Published on: June 16, 2014

18.1K
Optical Trap Loading of Dielectric Microparticles In Air
08:57

Optical Trap Loading of Dielectric Microparticles In Air

Published on: February 5, 2017

9.0K

Related Experiment Videos

Last Updated: Jun 11, 2025

Screening of Coatings for an All-Solid-State Battery Using In Situ Transmission Electron Microscopy
07:20

Screening of Coatings for an All-Solid-State Battery Using In Situ Transmission Electron Microscopy

Published on: January 20, 2023

2.5K
In Situ SIMS and IR Spectroscopy of Well-defined Surfaces Prepared by Soft Landing of Mass-selected Ions
10:22

In Situ SIMS and IR Spectroscopy of Well-defined Surfaces Prepared by Soft Landing of Mass-selected Ions

Published on: June 16, 2014

18.1K
Optical Trap Loading of Dielectric Microparticles In Air
08:57

Optical Trap Loading of Dielectric Microparticles In Air

Published on: February 5, 2017

9.0K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Electrical Engineering

Background:

  • Edge terminals face challenges with large, slow insulator detection models.
  • Efficient deployment of AI for infrastructure monitoring is crucial.

Purpose of the Study:

  • To develop a lightweight and fast insulator detection algorithm for edge devices.
  • To improve the accuracy and efficiency of visible light insulator target detection.

Main Methods:

  • Replaced VGG-16 with Ghost Module network for lightweight feature extraction.
  • Integrated FPN+PAN and SimSPPF for feature integration, and scSE attention mechanisms.
  • Optimized detection heads, employed DIoU-NMS, channel pruning, and knowledge distillation.

Main Results:

  • Reduced model parameters from 26.15 M to 0.61 M.
  • Decreased computational load from 118.95 G to 1.49 G.
  • Increased mean Average Precision (mAP) from 96.8% to 98%.

Conclusions:

  • The proposed lightweight algorithm significantly enhances detection speed and reduces model volume.
  • Achieved superior performance compared to existing models, ensuring detection accuracy.
  • Provides a viable solution for visible light insulator detection using edge intelligence.