Welcome to the Podiatry Arena forums

You are currently viewing our podiatry forum as a guest which gives you limited access to view all podiatry discussions and access our other features. By joining our free global community of Podiatrists and other interested foot health care professionals you will have access to post podiatry topics (answer and ask questions), communicate privately with other members, upload content, view attachments, receive a weekly email update of new discussions, access other special features. Registered users do not get displayed the advertisements in posted messages. Registration is fast, simple and absolutely free so please, join our global Podiatry community today!

  1. Sponsored Content: The Interpod Keystone for measuring supination resistance. Read about it here for more.
    Dismiss Notice
  2. Have you considered the Clinical Biomechanics Boot Camp Online, for taking it to the next level? See here for more.
    Dismiss Notice
Dismiss Notice
Have you considered the Clinical Biomechanics Boot Camp Online, for taking it to the next level? See here for more.
Dismiss Notice
Do you get the weekly newsletter that Podiatry Arena sends out to update everybody? If not, click here to organise this.

Using microsoft XBox kinect as a gait analysis system

Discussion in 'Biomechanics, Sports and Foot orthoses' started by toomoon, Apr 9, 2013.

  1. toomoon

    toomoon Well-Known Member


    Members do not see these Ads. Sign Up.
    Our latest paper just published from our group at Melbourne University. Why pay thousands for a gait analysis system when microsoft has paid millions to develop it for you?
    Reliability and validity of the Microsoft Kinect for evaluating static foot posture
    Benjamin F Mentiplay, Ross A Clark, Alexandra Mullins, Adam L Bryant, Simon Bartold and Kade Paterson. Journal of Foot and Ankle Research 2013, 6:14

    Abstract (provisional)
    Background
    The evaluation of foot posture in a clinical setting is useful to screen for potential injury, however disagreement remains as to which method has the greatest clinical utility. An inexpensive and widely available imaging system, the Microsoft KinectTM, may possess the characteristics to objectively evaluate static foot posture in a clinical setting with high accuracy. The aim of this study was to assess the intra-rater reliability and validity of this system for assessing static foot posture.

    Methods
    Three measures were used to assess static foot posture; traditional visual observation using the Foot Posture Index (FPI), a 3D motion analysis (3DMA) system and software designed to collect and analyse image and depth data from the Kinect. Spearman's rho was used to assess intra-rater reliability and concurrent validity of the Kinect to evaluate foot posture, and a linear regression was used to examine the ability of the Kinect to predict total visual FPI score.

    Results
    The Kinect demonstrated moderate to good intra-rater reliability for four FPI items of foot posture (rho = 0.62 to 0.78) and moderate to good correlations with the 3DMA system for four items of foot posture (rho = 0.51 to 0.85). In contrast, intra-rater reliability of visual FPI items was poor to moderate (rho = 0.17 to 0.63), and correlations with the Kinect and 3DMA systems were poor (absolute rho = 0.01 to 0.44). Kinect FPI items with moderate to good reliability predicted 61% of the variance in total visual FPI score.

    Conclusions
    The majority of the foot posture items derived using the Kinect were more reliable than the traditional visual assessment of FPI, and were valid when compared to a 3DMA system. Individual foot posture items recorded using the Kinect were also shown to predict a moderate degree of variance in the total visual FPI score. Combined, these results support the future potential of the Kinect to accurately evaluate static foot posture in a clinical setting.
    Full paper available at http://www.jfootankleres.com/content/pdf/1757-1146-6-14.pdf
     
  2. Ian Drakard

    Ian Drakard Active Member

    Thanks Simon

    I think this is a really interesting area. I've been using kinect or similar for a couple of months, originally for foot and cast scanning for orthotics, but have become really interested in the assessment potential with this. Is there any work on dynamic assessment in the pipeline?

    Kind regards
    Ian
     
  3. toomoon

    toomoon Well-Known Member

    Hi Ian.. we have been using it for dynamic assessment for some time, and plan to validate it against some of the very expensive 3D kinematic systems, where i expect it to excel.
    I do not think people really understand how much motion analysis gadgetry goes into this $120 odd piece of equipment. it is absolutely amazing!
     
  4. javier

    javier Senior Member

    I have been toying with a Asus Xtion Pro 3D Sensor (better than Microsoft Kinect because RGB image quality) for some weeks.

    Here is a comparision between depth sensors: http://wiki.ipisoft.com/Depth_Sensors_Comparison

    It can be used as a ultra low cost 3D scanner and for clinical gait analysis. But there is no algorithm developed for object detection, segmentation and classification useful for clinical gait analysis for now. Although, there are some promising projects.

    I attach a video from a 3D scanner from my foot as an example

     
    Last edited by a moderator: Sep 22, 2016
  5. toomoon

    toomoon Well-Known Member

    "But there is no algorithm developed for object detection, segmentation and classification useful for clinical gait analysis for now'.
    Dr Ross Clarke has written the algorithm for the Kinect and it works a treat!
     
  6. javier

    javier Senior Member

    I have read the paper you provided, I liked very much but they used an SDK app from National Instruments :

    "Custom made LabVIEW software (National Instruments, U.S.A.) was used to collect and analyse the data from the Kinect using the Microsoft Software Development Kit (SDK) Beta 2 (Microsoft, U.S.A.). Data were sampled at the native frequency of the Kinect, which is irregular at ≈ 30Hz. The depth image was converted to the same resolution as the video image using interpolation, and the two images were aligned using a cross correlation function. "


    Here it lies the problem regarding Depth Sensors for clinical gait analysis:

    "The real world coordinates of the pixels in the video and depth images were determined using the calibration data extracted from the SDK. When anatomical landmarks or specific positions needed to be identified, these were located using the video image and the corresponding points on the depth map were extracted. For all values the median of five consecutive frames of Kinect data were used."

    The study was related to evaluate static foot posture not dynamic gait analysis. It is necesary somekind of dynamic object detection algorithm such as this for hand:

     
    Last edited by a moderator: Sep 22, 2016
  7. toomoon

    toomoon Well-Known Member

    i am not talking about the study Javier.. I am talking about what they are working on next
     
  8. javier

    javier Senior Member

    I ask you to keep us updated about Dr Clark an coworkers research. I truly believe there is a great potential regarding depth sensors for podiatric clinical practice. Although there are better options than Kinect on the market. Thanks.
     
  9. toomoon

    toomoon Well-Known Member

  10. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Validity and reliability of the Kinect within functional assessment activities: Comparison with standard stereophotogrammetry
    B. Bonnechère et al
    Gait & Posture; Available online 5 October 2013
     
  11. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease.
    Galna B, Barry G, Jackson D, Mhiripiri D, Olivier P, Rochester L.
    Gait Posture. 2014 Jan 22.
     
  12. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Suitability of Kinect for measuring whole body movement patterns during exergaming.
    van Diest M, Stegenga J, Wörtche HJ, Postema K, Verkerke GJ, Lamoth CJ.
    J Biomech. 2014 Aug 15.
     
  13. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Validity of Kinect for Assessment of Joint Motion during Gait
    Muhammad Rijal Abdurrahman et al
    Applied Mechanics and Materials, 660, 921 2014
     
  14. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Kinect as a Tool for Gait Analysis: Validation of a Real-Time
    Joint Extraction Algorithm Working in Side View

    Enea Cippitelli , Samuele Gasparrini, Susanna Spinsante and Ennio Gambi
    Sensors 2015, 15
     
  15. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    The validity of the first and second generation Microsoft Kinect™ for identifying joint center locations during static postures
    Xu Xu, , Raymond W. McGorry
    Applied Ergonomics; Volume 49, July 2015, Pages 47–54
     
  16. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Reliability and concurrent validity of the Microsoft Kinect V2 for assessment of standing balance and postural control
    Ross A Clark, Yong-Hao Pua, Cristino C Oliveira, Kelly J Bower, Shamala Thilarajah, Rebekah McGaw, Ksaniel Hasanki, Benjamin F Mentiplay
    Gait and Posture; in press
     
  17. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Gait assessment using the Microsoft Xbox One Kinect: Concurrent validity and inter-day reliability of spatiotemporal and kinematic variables
    Benjamin F. Mentiplay, Luke G. Perraton, Kelly J. Bower, Yong-Hao Pua, Rebekah McGaw, Sophie Heywood, Ross A. Clark
    Journal of Biomechanics; Available online 28 May 2015
     
  18. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Accuracy of KinectOne to quantify kinematics of the upper body
    Roman P. Kuster, Bernd Heinlein, Christoph M. Bauer, Eveline S. Graf
    Gait and Posture; Article in Press
     
  19. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    The efficacy of the Microsoft KinectTM to assess human bimanual coordination
    Joshua J. Liddy , Howard N. Zelaznik, Jessica E. Huber, Shirley Rietdyk, Laura J. Claxton, Arjmand Samuel, Jeffrey M. Haddad
    Behavior Research Methods; 28 June 2016
     
  20. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Validity and sensitivity of the Longitudinal Asymmetry Index to detect gait asymmetry using Microsoft Kinect data
    E. Auvinet et al
    Gait and Posture; Article in Press
     
  21. NewsBot

    NewsBot The Admin that posts the news.

    Articles:
    1
    Using data from the Microsoft Kinect 2 to determine postural stability in healthy subjects: A feasibility trial.
    Dehbandi B et al
    PLoS One. 2017 Feb 14;12(2):e0170890. doi: 10.1371/journal.pone.0170890. eCollection 2017.
     
Loading...

Share This Page