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

Biodegradable microplastics disrupt root exudate driven plant-microbe interactions, compromising plant growth and rhizosphere microenvironment health.

Journal of hazardous materials·2026
Same author

Restricted cubic spline analysis of treatment duration before tocilizumab withdrawal and relapse risk in rheumatoid arthritis.

Therapeutic advances in musculoskeletal disease·2026
Same author

Gradient Anisotropic Natural Rubber-PNIPAM Composite Hydrogels for Programmable NIR-Responsive Actuation.

Gels (Basel, Switzerland)·2026
Same author

Controlled Synthesis of TiO<sub>2</sub> Nanotube Array-Based Slippery Liquid-Infused Porous Surfaces with Durable Liquid-Holding Property and Anti-Icing Performance.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

Integrating laboratory tests with FIGO staging using machine learning improves long-term prognostic assessment in endometrial cancer.

European journal of obstetrics, gynecology, and reproductive biology·2026
Same author

A data-driven framework for assessing structural heterogeneity and nonlinear performance in university sports governance.

Scientific reports·2026

Related Experiment Video

Updated: Jan 15, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Attention-Enhanced Semantic Segmentation for Substation Inspection Robot Navigation.

Changqing Cai1, Yongkang Yang1, Kaiqiao Tian2

  • 1College of Electrical and Information Engineering, Changchun Institute of Technology, 395 Kuan Ping Road, Changchun 130103, China.

Sensors (Basel, Switzerland)
|October 16, 2025
PubMed
Summary

This study introduces an autonomous robot for inspecting outdoor substations, overcoming challenges like poor lighting and obstructions. The robot uses enhanced semantic segmentation and GPS navigation for accurate, reliable infrastructure inspection.

Keywords:
DeepLabV3+attention mechanismautonomous inspection robotmultimodal perceptionnavigation line fittingsemantic segmentation

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

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

9.6K
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

3.3K

Related Experiment Videos

Last Updated: Jan 15, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

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

9.6K
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

3.3K

Area of Science:

  • Robotics and Automation
  • Computer Vision
  • Artificial Intelligence

Background:

  • Outdoor substations present significant inspection challenges due to uneven terrain, variable lighting, and occlusions.
  • Existing autonomous systems struggle with the complexity of these environments, limiting reliable robotic inspection.

Purpose of the Study:

  • To develop an embedded inspection robot capable of reliable autonomous operation in challenging outdoor substation environments.
  • To enhance semantic segmentation and GPS-assisted navigation for improved robotic inspection accuracy and robustness.

Main Methods:

  • An embedded inspection robot integrating an attention-enhanced DeepLabV3+ semantic segmentation model with GPS-assisted navigation.
  • Incorporation of ECA-SimAM and CBAM attention modules, plus a GPS-guided attention component for refined feature focus.
  • Utilizing RTK-GPS for global positioning and generating navigation lines from segmentation outputs for waypoint-based behaviors.

Main Results:

  • The proposed method achieved 85.26% mean IoU and 89.45% mean pixel accuracy in segmentation.
  • Performance surpassed U-Net, PSPNet, HRNet, and standard DeepLabV3+ in challenging conditions.
  • Successful deployment and validation on an embedded platform in real substation environments.

Conclusions:

  • The developed system demonstrates robust and scalable autonomous inspection capabilities for outdoor substations.
  • The integration of attention-enhanced semantic segmentation and GPS navigation effectively addresses environmental challenges.
  • The system offers a practical solution for enhancing the efficiency and safety of infrastructure inspection.