Markerless knee joint position measurement using depth data during stair walking

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Climbing and descending stairs are demanding daily activities, and the monitoring of them may reveal the presence of musculoskeletal diseases at an early stage. A markerless system is needed to monitor such stair walking activity without mentally or physically disturbing the subject. Microsoft Kinect v2 has been used for gait monitoring, as it provides a markerless skeleton tracking function. However, few studies have used this device for stair walking monitoring, and the accuracy of its skeleton tracking function during stair walking has not been evaluated. Moreover, skeleton tracking is not likely to be suitable for estimating body joints during stair walking, as the form of the body is different from what it is when it walks on level surfaces. In this study, a new method of estimating the 3D position of the knee joint was devised that uses the depth data of Kinect v2. The accuracy of this method was compared with that of the skeleton tracking function of Kinect v2 by simultaneously measuring subjects with a 3D motion capture system. The depth data method was found to be more accurate than skeleton tracking. The mean error of the 3D Euclidian distance of the depth data method was 43.2 ± 27.5 mm, while that of the skeleton tracking was 50.4 ± 23.9 mm. This method indicates the possibility of stair walking monitoring for the early discovery of musculoskeletal diseases.

Original languageEnglish
Article number2698
JournalSensors (Switzerland)
Volume17
Issue number11
DOIs
Publication statusPublished - 2017 Nov 22

Fingerprint

depth measurement
Position measurement
Stairs
walking
Knee Joint
musculoskeletal system
Skeleton
Walking
Musculoskeletal Diseases
Monitoring
estimating
gait
Gait
Joints
Equipment and Supplies

Keywords

  • 3D motion capture system
  • Depth data
  • Gait measurement
  • Kinect v2
  • Knee joint position
  • Markerless measurement
  • Skeleton tracking
  • Stair climbing
  • Stair descending
  • VICON

ASJC Scopus subject areas

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

Cite this

Markerless knee joint position measurement using depth data during stair walking. / Ogawa, Ami; Mita, Akira; Yorozu, Ayanori; Takahashi, Masaki.

In: Sensors (Switzerland), Vol. 17, No. 11, 2698, 22.11.2017.

Research output: Contribution to journalArticle

@article{e380a0dcb0bf4bc1b2c3013e750a3d9d,
title = "Markerless knee joint position measurement using depth data during stair walking",
abstract = "Climbing and descending stairs are demanding daily activities, and the monitoring of them may reveal the presence of musculoskeletal diseases at an early stage. A markerless system is needed to monitor such stair walking activity without mentally or physically disturbing the subject. Microsoft Kinect v2 has been used for gait monitoring, as it provides a markerless skeleton tracking function. However, few studies have used this device for stair walking monitoring, and the accuracy of its skeleton tracking function during stair walking has not been evaluated. Moreover, skeleton tracking is not likely to be suitable for estimating body joints during stair walking, as the form of the body is different from what it is when it walks on level surfaces. In this study, a new method of estimating the 3D position of the knee joint was devised that uses the depth data of Kinect v2. The accuracy of this method was compared with that of the skeleton tracking function of Kinect v2 by simultaneously measuring subjects with a 3D motion capture system. The depth data method was found to be more accurate than skeleton tracking. The mean error of the 3D Euclidian distance of the depth data method was 43.2 ± 27.5 mm, while that of the skeleton tracking was 50.4 ± 23.9 mm. This method indicates the possibility of stair walking monitoring for the early discovery of musculoskeletal diseases.",
keywords = "3D motion capture system, Depth data, Gait measurement, Kinect v2, Knee joint position, Markerless measurement, Skeleton tracking, Stair climbing, Stair descending, VICON",
author = "Ami Ogawa and Akira Mita and Ayanori Yorozu and Masaki Takahashi",
year = "2017",
month = "11",
day = "22",
doi = "10.3390/s17112698",
language = "English",
volume = "17",
journal = "Sensors (Switzerland)",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "11",

}

TY - JOUR

T1 - Markerless knee joint position measurement using depth data during stair walking

AU - Ogawa, Ami

AU - Mita, Akira

AU - Yorozu, Ayanori

AU - Takahashi, Masaki

PY - 2017/11/22

Y1 - 2017/11/22

N2 - Climbing and descending stairs are demanding daily activities, and the monitoring of them may reveal the presence of musculoskeletal diseases at an early stage. A markerless system is needed to monitor such stair walking activity without mentally or physically disturbing the subject. Microsoft Kinect v2 has been used for gait monitoring, as it provides a markerless skeleton tracking function. However, few studies have used this device for stair walking monitoring, and the accuracy of its skeleton tracking function during stair walking has not been evaluated. Moreover, skeleton tracking is not likely to be suitable for estimating body joints during stair walking, as the form of the body is different from what it is when it walks on level surfaces. In this study, a new method of estimating the 3D position of the knee joint was devised that uses the depth data of Kinect v2. The accuracy of this method was compared with that of the skeleton tracking function of Kinect v2 by simultaneously measuring subjects with a 3D motion capture system. The depth data method was found to be more accurate than skeleton tracking. The mean error of the 3D Euclidian distance of the depth data method was 43.2 ± 27.5 mm, while that of the skeleton tracking was 50.4 ± 23.9 mm. This method indicates the possibility of stair walking monitoring for the early discovery of musculoskeletal diseases.

AB - Climbing and descending stairs are demanding daily activities, and the monitoring of them may reveal the presence of musculoskeletal diseases at an early stage. A markerless system is needed to monitor such stair walking activity without mentally or physically disturbing the subject. Microsoft Kinect v2 has been used for gait monitoring, as it provides a markerless skeleton tracking function. However, few studies have used this device for stair walking monitoring, and the accuracy of its skeleton tracking function during stair walking has not been evaluated. Moreover, skeleton tracking is not likely to be suitable for estimating body joints during stair walking, as the form of the body is different from what it is when it walks on level surfaces. In this study, a new method of estimating the 3D position of the knee joint was devised that uses the depth data of Kinect v2. The accuracy of this method was compared with that of the skeleton tracking function of Kinect v2 by simultaneously measuring subjects with a 3D motion capture system. The depth data method was found to be more accurate than skeleton tracking. The mean error of the 3D Euclidian distance of the depth data method was 43.2 ± 27.5 mm, while that of the skeleton tracking was 50.4 ± 23.9 mm. This method indicates the possibility of stair walking monitoring for the early discovery of musculoskeletal diseases.

KW - 3D motion capture system

KW - Depth data

KW - Gait measurement

KW - Kinect v2

KW - Knee joint position

KW - Markerless measurement

KW - Skeleton tracking

KW - Stair climbing

KW - Stair descending

KW - VICON

UR - http://www.scopus.com/inward/record.url?scp=85035099800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035099800&partnerID=8YFLogxK

U2 - 10.3390/s17112698

DO - 10.3390/s17112698

M3 - Article

C2 - 29165396

AN - SCOPUS:85035099800

VL - 17

JO - Sensors (Switzerland)

JF - Sensors (Switzerland)

SN - 1424-8220

IS - 11

M1 - 2698

ER -