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

Deer Antler Extract Promotes Osteoblast Differentiation and Improves Bone Microarchitecture in an Ovariectomy-Induced Osteoporosis Model.

Preventive nutrition and food science·2026
Same author

Lung Microbiome Dysbiosis in Pulmonary Fibrosis Induced by Multi-Walled Carbon Nanotubes and Bleomycin in Rats.

Medicina (Kaunas, Lithuania)·2026
Same author

Epidemiological surveillance and genomic characterisation of betacoronavirus in <i>Apodemus agrarius</i> from Gyeonggi and Gangwon Provinces<i>,</i> Republic of Korea, 2017-2019.

One health (Amsterdam, Netherlands)·2026
Same author

American Ginseng (<i>Panax quinquefolius</i>) Extracts (G1899) Ameliorate Immunosenescence via Regulation of T Cell Populations and Aging-Related Proteins in a Mouse Model Induced by D-Galactose and Tert-Butyl Hydroperoxide.

Current issues in molecular biology·2026
Same author

Fuzzy C-means clustering based vertical container stacking in container terminals.

Scientific reports·2026
Same author

Dammarenediol II enhances etoposide-induced apoptosis by targeting O-GlcNAc transferase and Akt/GSK3β/mTOR signaling in liver cancer.

Molecular oncology·2025

Related Experiment Video

Updated: Dec 25, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

592

Novel Method of Semantic Segmentation Applicable to Augmented Reality.

Tae-Young Ko1, Seung-Ho Lee2

  • 1Department of Electronic Engineering, Hanbat National University, Daejeon 34158, Korea.

Sensors (Basel, Switzerland)
|April 5, 2020
PubMed
Summary

This study introduces a novel semantic segmentation method for augmented reality (AR) applications. The technique achieves high accuracy and frame rates, enabling real-time AR experiences.

Keywords:
atrous pyramid pooling moduleaugmented realitybackpropagationconvolutional neural networkfully convolutional networkmodified dilated residual networksemantic segmentation

More Related Videos

Usability Evaluation of Augmented Reality: A Neuro-Information-Systems Study
05:43

Usability Evaluation of Augmented Reality: A Neuro-Information-Systems Study

Published on: November 30, 2022

2.7K
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

9.5K

Related Experiment Videos

Last Updated: Dec 25, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

592
Usability Evaluation of Augmented Reality: A Neuro-Information-Systems Study
05:43

Usability Evaluation of Augmented Reality: A Neuro-Information-Systems Study

Published on: November 30, 2022

2.7K
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

9.5K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Augmented Reality

Background:

  • Semantic segmentation is crucial for understanding scenes in augmented reality.
  • Existing methods often struggle with real-time performance and accuracy for small objects.

Purpose of the Study:

  • To propose a novel semantic segmentation method optimized for augmented reality.
  • To improve accuracy and maintain high frame rates for real-time AR applications.

Main Methods:

  • Utilized a modified dilated residual network for feature extraction and spatial information preservation.
  • Employed an atrous pyramid pooling module to effectively segment small objects.
  • Integrated backpropagation to refine the segmentation accuracy by adjusting network weights.

Main Results:

  • Achieved 82.8% and 89.8% mean intersection over union (mIOU) on Cityscapes and PASCAL VOC 2012 datasets, respectively.
  • Reached frame rates of 61 fps and 64.3 fps on the respective datasets.
  • Demonstrated performance exceeding 60 fps, suitable for natural AR applications.

Conclusions:

  • The proposed semantic segmentation method is highly accurate and efficient.
  • The high frame rates confirm its suitability for real-time augmented reality.
  • This method facilitates the development of more immersive and responsive AR experiences.