Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter July 18, 2014

Vision-based categorization of upper body motion impairments and post-stroke motion synergies

  • Babak Taati EMAIL logo , Jennifer Campos , Jeremy Griffiths , Mona Gridseth and Alex Mihailidis


Upper body motion impairment is a common after-effect of a stroke. We are developing a novel multisensory therapy system that makes use of augmented feedback and is expected to enhance rehabilitation outcomes. The first phase of the project involved developing algorithms to automatically differentiate between normal and impaired upper body motions. Seven healthy subjects performed two types scripted actions: (a) elbow flexion and extension and (b) reaching over via elbow flexion and shoulder flexion and adduction. Each action was repeated 10 times as each participant felt most comfortable and also 10 times simulating a common post-stroke impaired motion according to the literature. Principal component analysis was applied to the upper body trajectories during each action, as observed with a Kinect sensor, to extract the dominant modes of motion. Three classification algorithms and up to three motion modes were examined in order to distinguish between normal and impaired motions. A statistical analysis of the Kinect skeletal tracking data vs. manual annotation confirmed a significant bias in the tracking of an elevated shoulder joint. Despite this bias, leave-one-subject-out cross validation experiments confirmed the effectiveness of the proposed methods in detecting impaired motions (accuracy >95%), even when the impairment involved elevating a shoulder. A single, most dominant motion mode provided sufficient information for the binary classification task. The high accuracy rates validate the use of vision-based pose tracking technologies in identifying motion deficiencies.

Corresponding author: Babak Taati, PhD, Scientist, Intelligent Assistive Technology and Systems Lab (IATSL), University of Toronto, Toronto, Ontario, Canada; and Toronto Rehabilitation Institute, University Health Network, 500 University Ave., Toronto, Ontario, M5G 2A2, Canada, E-mail:


This work was partially supported through a MITACS NCE Strategic Project post-doctoral fellowship. The authors would also like to thank the Toronto Rehabilitation Institute.


1. Altschuler EL, Wisdom SB, Stone L, Foster C, Galasko D, Ramachandran VS. Rehabilitation of hemiparesis after stroke with a mirror. Lancet 1999;353:2035–36.10.1016/S0140-6736(99)00920-4Search in Google Scholar

2. Botvinick M, Cohen J. Rubber hands “feel” touch that eyes see. Nature 1998;391:765.10.1038/35784Search in Google Scholar PubMed

3. Rizzo A, Kim GJ. A SWOT analysis of the field of virtual reality rehabilitation and therapy. Presence: Teleoperators Virtual Environ 2005;14:119–146.10.1162/1054746053967094Search in Google Scholar

4. Gowland C, Stratford P, Ward M, Moreland J, Torresin W, Van Hullenaar S, et al. Measuring physical impairment and disability with the Chedoke–McMaster stroke assessment. Stroke 1993;24:58–63.10.1161/01.STR.24.1.58Search in Google Scholar

5. Taati B, Wang R, Huq R, Snoek J, Mihailidis A. Vision-based posture assessment to detect and categorize compensation during robotic rehabilitation therapy. Proc 4th IEEE/RAS–EMBS Intl Conf Biomedical Robotics and Biomechatronics, 2012.10.1109/BioRob.2012.6290668Search in Google Scholar

6. Shotton J, Fitzgibbon A, Cook M, Sharp T, Finocchio M, Moore R, et al. Real-time human pose recognition in parts from a single depth image. Proc 24th IEEE Intl Conf Computer Vision and Pattern Recognition, 2011.10.1109/CVPR.2011.5995316Search in Google Scholar

7. Dutta T. Evaluation of the Kinect™ sensor for 3-D kinematic measurement in the workplace. Appl Ergonomics 2011;43:645–9.10.1016/j.apergo.2011.09.011Search in Google Scholar PubMed

8. Clark RA, Pua YH, Fortin K, Ritchie C, Webster KE, Denehy L, et al. Validity of the Microsoft Kinect for assessment of postural control. Gait Posture 2012;6:372–7.10.1016/j.gaitpost.2012.03.033Search in Google Scholar PubMed

9. Agresti A. Categorical data analysis. New York: Wiley-Interscience, 2002.10.1002/0471249688Search in Google Scholar

10. Joachims T. Making large-scale SVM learning practical. In: Schölkopf B, Burges C, Smola A. Advances in kernel methods: support vector learning. Boston, MA: MIT Press, 1999:41–56.Search in Google Scholar

11. Breiman L. Random forests. Mac Learn 2001;45:15–32.Search in Google Scholar

12. Caruana R, Niculescu-Mizil A. An Empirical comparison of supervised learning algorithms. Proc 23rd Intl Conf Machine Learning, 2006.10.1145/1143844.1143865Search in Google Scholar

Received: 2013-5-3
Accepted: 2013-6-22
Published Online: 2014-7-18
Published in Print: 2014-9-1

©2014 by De Gruyter

Downloaded on 10.12.2023 from
Scroll to top button