Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Validity of Microsoft Kinecttm for Measuring Gait Parameters Publisher



Kharazi MR1, 2 ; Memari AH2 ; Shahrokhi A2, 3 ; Nabavi H3 ; Khorami S1 ; Rasooli AH2 ; Barnamei HR1 ; Jamshidian AR4 ; Mirbagheri MM2, 3, 5
Authors
Show Affiliations
Authors Affiliations
  1. 1. Rehabilitation and Sports Medicine Noorafshar Hospital, Tehran, Iran
  2. 2. Islamic Azad University of Science and Research Branch, School of Biomedical Engineering, Tehran, Iran
  3. 3. Department of Physical Medicine and Rehabilitation, Northwestern University, United States
  4. 4. Tehran University of Medical Sciences, School of Biomedical Engineering, Iran
  5. 5. Sheikhbahaee University, Mathematics and Computer Science Department, Baharestan, Isfahan, Iran

Source: 2015 22nd Iranian Conference on Biomedical Engineering# ICBME 2015 Published:2016


Abstract

The calculation of gait parameters requires motion tracking systems combined with force plates and EMG, which limits the measurement to laboratory settings. In recent studies, the possibility of using the portable, low cost, and markerless Microsoft KinectTM sensor to measure gait parameters on treadmill walking has been examined. The current study further examined the accuracy level of the KinectTM version 2 sensor for assessment of gait parameters during overground walking under different walking speeds versus Vicon system. Twenty-one healthy participants walked overground and a KinectTM sensor and a Vicon motion tracking system measured their full body kinematics data concurrently concurrently of Gait parameters like knee and hip joint angles were extracted from the two devices and were compared. The results showed that when using the Kinect sensor,the accuracy levels varied across the joint angles. The average r for ankle, knee and hip in both systems was 0.09, 0.95 and 0.98 respectively within all test and trials with 95% confidence interval.The average RMSE error for ankle,knee and hip was 22.03, 5.33 and 5.29 degrees respectively. We found a good agreement of kinect version 2 and Vicon system to track knee and hip joints. © 2015 IEEE.