Jove
Visualize
Contact Us

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

A Tablet Computer-Based Food Record for the Self-Assessment of Nutritional Intake in Patients Undergoing Geriatric Rehabilitation: Prospective Pilot Feasibility Study.

JMIR aging·2026
Same author

A Digital Assistive System for Maintaining Nutrition and Mobility in Older Adults: Usability and Feasibility Findings From a Pilot Study.

JMIR formative research·2026
Same author

Cross-sectional and prospective associations between jump performance and functional outcomes in older adults: a systematic review and meta-analysis.

BMC geriatrics·2026
Same author

Requirements for mHealth and Augmented Reality Apps for Patient Education Regarding Colorectal Cancer Surgery: Focus Group Study.

JMIR formative research·2026
Same author

Comparing Patient Simulation With a Humanoid Robot or a Human Actor in Terms of Training Success and Acceptance: Pilot Questionnaire Study.

JMIR formative research·2025
Same author

Validation and evaluation of a tablet-based dietary record app for adults aged 70 and above.

PloS one·2025
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: Aug 13, 2025

Influence of Step-Width Manipulation on Running Biomechanics
06:53

Influence of Step-Width Manipulation on Running Biomechanics

Published on: February 28, 2025

549

How the Processing Mode Influences Azure Kinect Body Tracking Results.

Linda Büker1, Vincent Quinten1, Michel Hackbarth2

  • 1Assistance Systems and Medical Device Technology, Department for Health Services Research, School of Medicine and Health Sciences, Carl von Ossietzky University, Ammerländer Heerstraße 114-118, 26129 Oldenburg, Germany.

Sensors (Basel, Switzerland)
|January 21, 2023
PubMed
Summary
This summary is machine-generated.

Azure Kinect body tracking results are inconsistent across different processing modes and computers. Careful selection of processing modes and consistent hardware are crucial for reproducible research findings.

Keywords:
Azure KinectAzure Kinect Body Tracking SDKbody trackingquality assurancereproducibilityskeleton tracking

More Related Videos

Movement Retraining using Real-time Feedback of Performance
08:16

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

13.5K
Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments
08:45

Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments

Published on: March 28, 2018

10.7K

Related Experiment Videos

Last Updated: Aug 13, 2025

Influence of Step-Width Manipulation on Running Biomechanics
06:53

Influence of Step-Width Manipulation on Running Biomechanics

Published on: February 28, 2025

549
Movement Retraining using Real-time Feedback of Performance
08:16

Movement Retraining using Real-time Feedback of Performance

Published on: January 17, 2013

13.5K
Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments
08:45

Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments

Published on: March 28, 2018

10.7K

Area of Science:

  • Biomedical Engineering
  • Human-Computer Interaction
  • Robotics

Background:

  • The Azure Kinect DK is a widely used RGB-D camera in human-centric research.
  • Ensuring consistency and reproducibility of Azure Kinect results is vital for scientific integrity.

Purpose of the Study:

  • To evaluate the consistency and reproducibility of Azure Kinect body tracking across different processing modes and hardware.
  • To identify factors contributing to result variability in Azure Kinect body tracking.

Main Methods:

  • 100 body tracking runs were analyzed per processing mode (CUDA, TensorRT, CPU, DirectML) on two distinct computers using prerecorded video.
  • Spatiotemporal progression, derived parameters (bone length), and inter-computer differences were compared.

Main Results:

  • A previously undocumented joint position converging behavior was observed at the start of tracking.
  • Clinically relevant Euclidean distance variations (up to 87 mm) were found between runs for CUDA and TensorRT modes.
  • CPU and DirectML modes showed no intra-computer differences, but noticeable inter-computer variations were detected.

Conclusions:

  • Processing mode significantly impacts Azure Kinect body tracking consistency; CUDA and TensorRT exhibit higher variability.
  • Inter-computer differences necessitate performing all analyses on a single machine for reproducibility.
  • Researchers should carefully select, report, and be cautious when interpreting Azure Kinect body tracking data from prior studies.