Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Display-based augmented reality navigation for CT-Guided thoracoabdominal punctures: phantom study of accuracy and workflow efficiency.

Biomedical physics & engineering express·2026

Same author

Application of an effective marker-less augmented reality image guidance method in dental implant surgery.

The international journal of medical robotics + computer assisted surgery : MRCAS·2023

Same author

Augmented reality for oral and maxillofacial surgery: The feasibility of a marker-free registration method.

The international journal of medical robotics + computer assisted surgery : MRCAS·2022

Same author

Marker-less augmented reality based on monocular vision for falx meningioma localization.

The international journal of medical robotics + computer assisted surgery : MRCAS·2021

Same author

Haptic-based virtual reality simulator for lateral ventricle puncture operation.

The international journal of medical robotics + computer assisted surgery : MRCAS·2020

Search research articles

Related Experiment Video

Updated: Jun 27, 2026

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

A Low-Cost RGB-D Sensing Front-End for Stable 3D Hand Landmark Reconstruction Using MediaPipe and ZED2 Stereo Depth.

Laixin Peng^1,2, Tiansheng Liu^1,2, Bingwei He^1,2

¹School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China.

Sensors (Basel, Switzerland)

|June 26, 2026

Summary

This study introduces a new RGB-D sensing system for accurate 3D hand landmark reconstruction. The lightweight system combines semantic landmarks with stereo depth for improved human-computer interaction and motion analysis.

Keywords:

3D hand landmark reconstruction MediaPipe RGB-D sensing ZED2 bone-length constraint hand motion tracking sensor fusion stereo depth temporal filtering

More Related Videos

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

Related Experiment Videos

Last Updated: Jun 27, 2026

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

Area of Science:

Computer Vision
Robotics
Human-Computer Interaction

Background:

RGB-based hand landmark detectors lack metric depth accuracy.
Stereo cameras offer metric depth but struggle with occlusions and noise.
Accurate 3D hand reconstruction is crucial for various interactive applications.

Purpose of the Study:

To develop a lightweight RGB-D sensing front-end for stable 3D hand landmark reconstruction.
To integrate semantic hand landmarks with stereo depth data for improved accuracy.
To enhance robustness against common depth sensing challenges.

Main Methods:

Combined MediaPipe semantic hand landmarks with ZED2 stereo depth data.
Employed local median sampling for landmark-level metric depth extraction.
Implemented exponential moving average filtering and bone-length consistency constraints for stabilization.

Main Results:

The proposed pipeline achieved stable 3D hand landmark reconstruction.
Local median sampling improved valid-depth ratio and temporal smoothness compared to single-pixel sampling.
Exponential moving average filtering and bone-length constraints balanced smoothing and motion fidelity.

Conclusions:

The developed RGB-D front-end offers a practical, low-cost solution for stable 3D hand landmark reconstruction.
The system is suitable for applications requiring precise hand tracking under controlled indoor conditions.
This approach addresses limitations of existing RGB and stereo depth methods.