Physical Therapy Korea (한국전문물리치료학회지)

Korean Research Society of Physical Therapy (한국전문물리치료학회)
권호 표지
DOI QR코드

DOI QR Code

Accuracy Comparison of Spatiotemporal Gait Variables Measured by the Microsoft Kinect 2 Sensor Directed Toward and Oblique to the Movement Direction

정면과 측면에 위치시킨 마이크로 소프트 키넥트 2로 측정한 보행 시공간 변인 정확성 비교

  • Hwang, Jisun (Department of Physical Therapy, Graduate School of Hoseo University) ;
  • Kim, Eun-jin (Department of Physical Therapy, Hoseo University) ;
  • Hwang, Seonhong (Department of Physical Therapy, Hoseo University)
  • 황지선 (호서대학교 일반대학원 물리치료학과) ;
  • 김은진 (호서대학교 생명보건대학 물리치료학과) ;
  • 황선홍 (호서대학교 생명보건대학 물리치료학과)
  • Received : 2018.06.11
  • Accepted : 2018.09.27
  • Published : 2019.02.19
Download PDF
⟨ Previous Next ⟩

Abstract

Background: The Microsoft Kinect which is a low-cost gaming device has been studied as a promise clinical gait analysis tool having satisfactory reliability and validity. However, its accuracy is only guaranteed when it is properly positioned in front of a subject. Objects: The purpose of this study was to identify the error when the Kinect was positioned at a $45^{\circ}$ angle to the longitudinal walking plane compare with those when the Kinect was positioned in front of a subject. Methods: Sixteen healthy adults performed two testing sessions consisting of walking toward and $45^{\circ}$ obliquely the Kinect. Spatiotemporal outcome measures related to stride length, stride time, step length, step time and walking speed were examined. To assess the error between Kinect and 3D motion analysis systems, mean absolute errors (MAE) were determined and compared. Results: MAE of stride length, stride time, step time and walking speed when the Kinect set in front of subjects were investigated as .36, .04, .20 and .32 respectively. MAE of those when the Kinect placed obliquely were investigated as .67, .09, .37, and .58 respectively. There were significant differences in spatiotemporal outcomes between the two conditions. Conclusion: Based on our study experience, positioning the Kinect directly in front of the person walking towards it provides the optimal spatiotemporal data. Therefore, we concluded that the Kinect should be placed carefully and adequately in clinical settings.

Keywords

References

  1. Chae YS. A serious game design and prototype development for rehabiltation using KINECT tools. J Korean Multimed Soc. 2014;17(2):248-256. https://doi.org/10.9717/kmms.2014.17.2.248
  2. Choi HS. Kinect-based motion recognition model for the 3D contents control. International Journal Of Contents. 2014;14(1):24-29.
  3. Chung CY, Park MS, Choi IH, et el. Three dimensional gait analysis in normal korean A preliminary report. J Korean Orthop Assoc. 2005;40(1):83-88. https://doi.org/10.4055/jkoa.2005.40.1.83
  4. Corazza S, Mundermann L, Chaudhari AM, et al. A markerless motion capture system to study musculoskeletal biomechanics: Visual hull and simulated annealing approach. Ann Biomed Eng. 2006;34(6):1019-1029. https://doi.org/10.1007/s10439-006-9122-8
  5. Daphne JG, Bert HC, Melvyn R. Kinematic validation of a multi-kinect v2 instrumented 10-meter walkway for quantitative gait assessments. PLoS ONE. 2015;10(10):1-15. https://doi.org/10.1371/journal.pone.0139913
  6. Hollmn JH, McDade EM, Petersen RC. Normative spatiotemporal gait parameters in older adults. Gait Posture. 2011;34(1):111-118. https://doi.org/10.1016/j.gaitpost.2011.03.024
  7. Jung GI. A New approach for measuring of stride length using optical method. Seoul, Konkuk University, Master Thesis. 2010.
  8. Kim CK, Son WJ. Trends analysis of animation technology using motion capture system. Journal of Korea Design Forum. 2008;19:203-211.
  9. Kim G, Yoon NM. A study on kinetic gait analysis of the normal adult. J Kor Soc Phys Ther. 2009;21(2):87-95.
  10. Kim JJ, Gwon SJ, Lee YS. Smart remote rehabilitation system based on the measurement of heart rate from ECG sensor and kinect motion-recognition. J Sens Sci Tech. 2015;24(1):69-77. https://doi.org/10.5369/JSST.2015.24.1.69
  11. Lee G, Cho CH, Lim KJ, et al. Efect of direction to be used for the timed up and go test on walking time in stroke patients. Phys Ther Kor. 2016;23(2):1-19. https://doi.org/10.12674/ptk.2016.23.2.011
  12. Mentiplay BF, Perraton LG, Bower KJ, et al. Gait assessment using the Microsoft Xbox One Kinect: Concurrent validity and inter-day reliability of spatiotemporal and kinematic variables. J Biomech. 2015;48(10):2166-2170. https://doi.org/10.1016/j.jbiomech.2015.05.021
  13. Oh YS, Woo YK. The effects of backward walking training with inclined treadmil on the gait in chronic stroke patients. Phys Ther Kor. 2016;23(3):1-10. https://doi.org/10.12674/ptk.2016.23.3.001
  14. Pfister A, West AM, Bronner S, et al. Comparative abilities of Microsoft Kinect and Vicon 3D motion capture for gait analysis. J Med Eng Technol. 2014;38(5):274-280. https://doi.org/10.3109/03091902.2014.909540
  15. Valmassy R. Clinical Biomechanics of the Lower Extremities. Height. MD, MO. Mosby, 1996.
  16. Xu X, McGorry RW, Chou LS, et al. Accuracy of the Microsoft Kinect for measuring gait parameters during treadmill walking. Gait Posture. 2015;42(2):145-151. https://doi.org/10.1016/j.gaitpost.2015.05.002
  17. Yang HD. Conditional random field based gesture recognition with Kinect sensor. Journal of KISS : Software and applications. 2013;40(11);716-723.
  18. Yang ST, Kang DW, Seo JW, et al. Evaluation of balance ability of the elderly using kinect sensor. Trans Korean Inst Electr Eng. 2017;66(2):439-446. https://doi.org/10.5370/KIEE.2017.66.2.439