Improving Movement Analysis in Physical Therapy Systems Based on Kinect Interaction

This study uses machine learning methods to analyse Kinect body gestures involved in the user interaction with exergaming systems designed for physical rehabilitation. We propose a method to improve gesture recognition accuracy and motion analysis, by extracting from the full body motion data recorded by the Kinect sensor three important features which are relevant to physical therapy exercises: body posture, movement trajectory and range of motion. By applying the Hidden Markov Model (HMM) and Dynamic Time Warping (DTW) algorithms, we obtained an improved accuracy by selecting specific features from the public UTD-MHAD full body gestures database (with up to 56% for HMM and 32% for DTW). Preliminary results show a positive correlation between the movement amplitude and the envelope feature (r = 0.92). Thus, this approach has the potential to improve gesture recognition accuracy and provide user feedback on how to improve the movement performed, in particular the movement amplitude. We propose further improvements and method validations to be the basis of creating an intelligent virtual rehabilitation assistant.

Content

Author and article information

Contributors

Alina D. Călin

Horia F. Pop

Rareş F. Boian

Conference

Publication date: July 2017

Publication date (Print): July 2017

Pages: 1-5

Affiliations

[0001]Department of Computer Science

Babeş-Bolyai University

1 Mihail Kogalniceanu Street

RO-400084 Cluj-Napoca, Romania

Article

DOI: 10.14236/ewic/HCI2017.87

SO-VID: 160f73d1-de0f-4715-ab1f-dc589dceac67

License:

This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

Conference name: Proceedings of the 31st International BCS Human Computer Interaction Conference (HCI 2017)

Conference acronym: HCI

Conference number: 31

Conference location: Sunderland, UK

Conference date: 3 - 6 July 2017

Conference sponsor: Electronic Workshops in Computing (eWiC)

Conference theme: digital make-believe, with delegates considering our expansive

History

Product

1477-9358 BCS Learning & Development

Self URI (article page): https://www.scienceopen.com/hosted-document?doi=10.14236/ewic/HCI2017.87

Self URI (journal page): https://ewic.bcs.org/

refference

A. D. Câlin 2016 Variation of Pose and Gesture Recognition Accuracy Using Two Kinect Versions International Symposium on INnovations in Intelligent SysTems and Applications 1 7
A. D. Câlin 2016 Gesture Recognition on Kinect Time Series Data Using Dynamic Time Warping and Hidden Markov Models International Symposium on Symbolic and Numeric Algorithms for Scientific Computing 264 271
A. D. Câlin 2016 Time Series Kinect Gestures Database Available from https://goo.gl/ZzmE0a Dec 2016
C. ChenR. JafariN. Kehtarnavaz 2015 UTD-MHAD: A Multimodal Dataset for Human Action Recognition Utilizing a Depth Camera and a Wearable Inertial Sensor Proceedings of IEEE International Conference on Image Processing Canada 168 172
F. GrimmG. NarosA. Gharabaghi 2016 Compensation or Restoration: Closed-loop Feedback of Movement Quality for Assisted Reach-to-grasp Exercises with a Multi-joint Arm Exoskeleton Frontiers in Neuroscience 10
J. F. LinD. Kulic 2012 Segmenting Human Motion for Automated Rehabilitation Exercise Analysis Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2881 2884
Microsoft Corporation 2017 Microsoft Kinect for Windows, Version 2 Available from https://developer.microsoft.com/en-us/windows/kinect Mar 2017
MIRA Rehab Limited 2017 Available from http://www.mirarehab.com May 2017
G. NicholasA. P. Joseph 2014 The Gesture Recognition Toolkit Available from https://github.com/nickgillian/grt Nov 2016
Q. Wang et al 2015 Evaluation of Pose Tracking Accuracy in the First and Second Generations of Microsoft Kinect International Conference on Healthcare Informatics 380 389

Comments

Comment on this article

[1] A. D. Câlin 2016 Variation of Pose and Gesture Recognition Accuracy Using Two Kinect Versions International Symposium on INnovations in Intelligent SysTems and Applications 1 7

[2] A. D. Câlin 2016 Gesture Recognition on Kinect Time Series Data Using Dynamic Time Warping and Hidden Markov Models International Symposium on Symbolic and Numeric Algorithms for Scientific Computing 264 271

[3] A. D. Câlin 2016 Time Series Kinect Gestures Database Available from https://goo.gl/ZzmE0a Dec 2016

[4] C. ChenR. JafariN. Kehtarnavaz 2015 UTD-MHAD: A Multimodal Dataset for Human Action Recognition Utilizing a Depth Camera and a Wearable Inertial Sensor Proceedings of IEEE International Conference on Image Processing Canada 168 172

[5] F. GrimmG. NarosA. Gharabaghi 2016 Compensation or Restoration: Closed-loop Feedback of Movement Quality for Assisted Reach-to-grasp Exercises with a Multi-joint Arm Exoskeleton Frontiers in Neuroscience 10

[6] J. F. LinD. Kulic 2012 Segmenting Human Motion for Automated Rehabilitation Exercise Analysis Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2881 2884

[7] Microsoft Corporation 2017 Microsoft Kinect for Windows, Version 2 Available from https://developer.microsoft.com/en-us/windows/kinect Mar 2017

[8] MIRA Rehab Limited 2017 Available from http://www.mirarehab.com May 2017

[9] G. NicholasA. P. Joseph 2014 The Gesture Recognition Toolkit Available from https://github.com/nickgillian/grt Nov 2016

[10] Q. Wang et al 2015 Evaluation of Pose Tracking Accuracy in the First and Second Generations of Microsoft Kinect International Conference on Healthcare Informatics 380 389

Studying business & IT? Drive your professional career forwards with BCS books - for a 20% discount click here: shop.bcs.org