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 Experiment Video

Updated: May 25, 2026

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

TransitNet: A lightweight semantic segmentation network for urban traffic scene understanding.

Haiyan Zhang1, Zining Zhao1, Xiang Chu1

  • 1Huaiyin Institute of Technology, Huaian, China.

Plos One
|May 22, 2026
PubMed
Summary

TransitNet is a lightweight semantic segmentation network designed for resource-constrained systems. It achieves high accuracy and cross-domain adaptability for tasks like autonomous driving and remote sensing.

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 Different Maceration Times on the Chemical and Sensory Characteristics of Cabernet Sauvignon Grapes Wine.

Foods (Basel, Switzerland)·2026
Same author

Diallyl Disulfide Mitigates LPS-Induced Inhibition of Osteogenic Differentiation and Alleviates Inflammatory Bone Loss via PI3K/AKT Signaling Pathway.

Drug design, development and therapy·2026
Same author

Ultra-Low Loading Pseudo-Single-Crystal Mesoporous PtPd Catalysts for High-Performance Hydrogen Gas Batteries.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Platelet Cyclophilin D Drives Cholesterol Crystal Embolism-Related Acute Kidney Injury and Kidney Infarction.

Journal of the American Society of Nephrology : JASN·2026
Same author

In Situ Transformed Organic Redox Molecules for a Hydrogen Battery Operated at -70 °C.

ACS nano·2026
Same author

Vertically Aligned Metal-Organic Framework Arrays as Protective Layers for Durable Zinc Anodes with Low Overpotentials.

Angewandte Chemie (International ed. in English)·2025

Area of Science:

  • Computer Vision
  • Machine Learning
  • Deep Learning

Background:

  • Existing semantic segmentation networks are computationally intensive and lack cross-domain adaptability.
  • Deployment on edge devices and in-vehicle systems is challenging due to large model sizes.
  • Diverse scenarios like traffic and remote sensing require robust segmentation models.

Purpose of the Study:

  • To propose TransitNet, a lightweight semantic segmentation network with enhanced cross-domain adaptation.
  • To improve performance on resource-constrained systems and diverse environmental perception tasks.
  • To balance efficiency and accuracy for real-time applications.

Main Methods:

  • TransitNet is based on PSPNet architecture, incorporating Rectangular Context Calibration Attention (RCCA) and Bidirectional Fusion Attention (BFA) modules.

More Related Videos

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Related Experiment Videos

Last Updated: May 25, 2026

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

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • A novel StarNet backbone utilizing star-shaped operations and depthwise separable convolutions reduces model parameters.
  • An improved forward propagation mechanism supports multi-scale feature fusion.

    • Main Results:

    • TransitNet achieved 86.98% mIoU on VOC2012, outperforming PSPNet by 1.58%.
    • On the LoveAD dataset, it reached 61.04% mIoU, surpassing CM-UNet by 8.87%.
    • An mIoU of 76.11% on OST300 demonstrates strong generalization and cross-domain adaptation.

    Conclusions:

    • TransitNet offers a high-performance, efficient semantic segmentation solution for autonomous driving and remote sensing.
    • Its lightweight design and cross-domain capabilities make it suitable for edge deployment.
    • The model shows significant potential for fine classification tasks in various imagery datasets.