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

Trustworthy AI for personalized glycemic control: a systematic review and critical appraisal of multimodal forecasting and safety-critical closed-loop control.

Reviews in endocrine & metabolic disorders·2026
Same author

AutoBiGluNet: transformer-based time series modeling for blood glucose prediction in Type 1 diabetes patients.

Health information science and systems·2026
Same author

Metabolically Faithful 3D PET Restoration via Volumetric Swin Transformers.

Neuroinformatics·2026
Same author

GAT-BiGRU: explainable multi-task temporal graph learning for glucose forecasting, hypoglycemia risk, and counterfactual insulin adjustment.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Interpretable CRAM‑Enhanced Lightweight Dual‑Branch CNN for Real‑Time Breast Cancer Histopathology in Internet‑of‑Medical‑Things Environments.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Systematic review of Artificial Intelligence-based methods for glycemic control and risk prediction in intensive care units.

Artificial intelligence in medicine·2026

Related Experiment Video

Updated: Nov 9, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.7K

Detection of sitting posture using hierarchical image composition and deep learning.

Audrius Kulikajevas1, Rytis Maskeliunas1, Robertas Damaševičius2,3

  • 1Department of Multimedia Engineering, Kaunas University of Technology, Kaunas, Lithuania.

Peerj. Computer Science
|April 9, 2021
PubMed
Summary

This study introduces a novel deep recurrent hierarchical network (DRHN) for accurate human posture detection, even with occluded torsos. The model achieves high accuracy for recognizing sitting postures using RGB-Depth data.

Keywords:
Artificial neural networkComputer visionDeep learningDepth sensorsPosture detectionSitting posturee-Health

More Related Videos

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

751
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.4K

Related Experiment Videos

Last Updated: Nov 9, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.7K
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

751
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.4K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Human-Computer Interaction

Background:

  • Human posture detection is crucial for applications in healthcare, rehabilitation, and assisted living.
  • Traditional methods struggle with occlusions and limited visibility of the human torso.
  • Advancements in deep learning and computer vision offer potential solutions.

Purpose of the Study:

  • To propose a novel deep recurrent hierarchical network (DRHN) for robust human posture detection.
  • To address the challenge of torso occlusion in posture recognition.
  • To develop a flexible model utilizing RGB-Depth frame sequences.

Main Methods:

  • A novel deep recurrent hierarchical network (DRHN) model was developed.
  • The model is based on the MobileNetV2 architecture.
  • It processes RGB-Depth frame sequences to identify posture states.

Main Results:

  • The DRHN model demonstrated high accuracy in human posture detection.
  • Achieved 91.47% accuracy for sitting posture recognition.
  • Operates at a rate of 10 frames per second (fps).

Conclusions:

  • The proposed DRHN model effectively handles torso occlusion in human posture detection.
  • The model offers a flexible and accurate solution for posture recognition tasks.
  • This approach has significant implications for healthcare and rehabilitation technologies.