Agreement between Azure Kinect and Marker-Based Motion Analysis during Functional Movements: A Feasibility Study

Sungbae Jo, Sunmi Song, Junesun Kim, Changho Song

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

(1) Background: The present study investigated the agreement between the Azure Kinect and marker-based motion analysis during functional movements. (2) Methods: Twelve healthy adults participated in this study and performed a total of six different tasks including front view squat, side view squat, forward reach, lateral reach, front view lunge, and side view lunge. Movement data were collected using an Azure Kinect and 12 infrared cameras while the participants performed the movements. The comparability between marker-based motion analysis and Azure Kinect was visualized using Bland–Altman plots and scatter plots. (3) Results: During the front view of squat motions, hip and knee joint angles showed moderate and high level of concurrent validity, respectively. The side view of squat motions showed moderate to good in the visible hip joint angles, whereas hidden hip joint angle showed poor concurrent validity. The knee joint angles showed variation between excellent and moderate concurrent validity depending on the visibility. The forward reach motions showed moderate concurrent validity for both shoulder angles, whereas the lateral reach motions showed excellent concurrent validity. During the front view of lunge motions, both the hip and knee joint angles showed moderate concurrent validity. The side view of lunge motions showed variations in concurrent validity, while the right hip joint angle showed good concurrent validity; the left hip joint showed poor concurrent validity. (4) Conclusions: The overall agreement between the Azure Kinect and marker-based motion analysis system was moderate to good when the body segments were visible to the Azure Kinect, yet the accuracy of tracking hidden body parts is still a concern.

Original languageEnglish
Article number9819
JournalSensors
Volume22
Issue number24
DOIs
Publication statusPublished - 2022 Dec

Bibliographical note

Funding Information:
This research was supported by a grant from the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number: HI21C0572).

Publisher Copyright:
© 2022 by the authors.

Keywords

  • 3D motion analysis
  • activities of daily living
  • depth sensor
  • motion capture

ASJC Scopus subject areas

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Agreement between Azure Kinect and Marker-Based Motion Analysis during Functional Movements: A Feasibility Study'. Together they form a unique fingerprint.

Cite this