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

Amyloid PET Quantitation and Centiloid Thresholds in the Diagnosis of Alzheimer Disease: An Individual Participant Data Meta-Analysis.

JAMA·2026
Same author

SEM mapping of sequence-specific protein-DNA interactions on long DNA molecules.

Nucleic acids research·2026
Same author

The feasibility of [<sup>18</sup>F]PSMA-1007 PET/CT for response assessment in prostate cancer following neoadjuvant androgen deprivation therapy compared with mpMRI.

Cancer imaging : the official publication of the International Cancer Imaging Society·2026
Same author

Modal contrast engineering in ultraviolet and visible metalenses enabled by material-selective hybridization.

Nature communications·2026
Same author

Differentiable library-based inverse design of achromatic metalens for full-color near-eye displays.

Nature communications·2026
Same author

Early Detection of Biochemical Recurrence in Prostate Cancer Patients with PSA Levels ≤0.5 ng/mL; Comparison Study between [¹⁸F]PSMA-1007 and [⁶⁸Ga]Ga-PSMA-11 PET/CT.

The world journal of men's health·2026

Related Experiment Video

Updated: Apr 11, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

1.5K

Real-time human pose estimation and gesture recognition from depth images using superpixels and SVM classifier.

Hanguen Kim1, Sangwon Lee2, Dongsung Lee3

  • 1Urban Robotics Laboratory (URL), Dept. Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 305-338, Korea. sskhk05@kaist.ac.kr.

Sensors (Basel, Switzerland)
|May 29, 2015
PubMed
Summary

This study introduces CPU-based human pose and gesture recognition using only depth data, suitable for low-cost platforms. The methods achieve good performance in real-world scenarios.

Keywords:
depth informationgesture recognitionhuman pose estimationlow-cost platform

More Related Videos

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

5.7K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

2.4K

Related Experiment Videos

Last Updated: Apr 11, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

1.5K
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

5.7K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

2.4K

Area of Science:

  • Computer Vision
  • Human-Computer Interaction

Background:

  • Traditional human pose and gesture recognition often require significant computational resources or specialized hardware.
  • Developing efficient algorithms for low-cost platforms like embedded boards is crucial for broader accessibility.

Purpose of the Study:

  • To develop human pose estimation and gesture recognition algorithms utilizing solely depth information.
  • To ensure the algorithms are operable on a central processing unit (CPU) for low-cost applications.

Main Methods:

  • Human pose estimation employs support vector machines (SVM) and superpixels without a predefined human body model.
  • Gesture recognition is achieved by comparing extracted keyframes from input poses against a database of registered gestures.
  • Robustness to motion speed variations is addressed through keyframe extraction, and unregistered gesture rejection is managed by setting maximum allowable comparison errors.

Main Results:

  • The proposed human pose estimation and gesture recognition methods were evaluated on a custom-generated dataset.
  • Experimental results indicate that the developed algorithms perform effectively.
  • The methods demonstrate applicability in real-world environments.

Conclusions:

  • Depth-based human pose and gesture recognition is feasible using efficient CPU-implemented algorithms.
  • The approach offers a cost-effective solution for human-computer interaction on embedded systems.
  • The keyframe-based gesture recognition with error thresholding provides reliable performance.