Advanced search
1 file | 829.80 KB

Human gesture classification by brute-force machine learning for exergaming in physiotherapy

Author
Organization
Abstract
In this paper, a novel approach for human gesture classification on skeletal data is proposed for the application of exergaming in physiotherapy. Unlike existing methods, we propose to use a general classifier like Random Forests to recognize dynamic gestures. The temporal dimension is handled afterwards by majority voting in a sliding window over the consecutive predictions of the classifier. The gestures can have partially similar postures, such that the classifier will decide on the dissimilar postures. This brute-force classification strategy is permitted, because dynamic human gestures show sufficient dissimilar postures. Online continuous human gesture recognition can classify dynamic gestures in an early stage, which is a crucial advantage when controlling a game by automatic gesture recognition. Also, ground truth can be easily obtained, since all postures in a gesture get the same label, without any discretization into consecutive postures. This way, new gestures can be easily added, which is advantageous in adaptive game development. We evaluate our strategy by a leave-one-subject-out cross-validation on a self-captured stealth game gesture dataset and the publicly available Microsoft Research Cambridge-12 Kinect (MSRC-12) dataset. On the first dataset we achieve an excellent accuracy rate of 96.72%. Furthermore, we show that Random Forests perform better than Support Vector Machines. On the second dataset we achieve an accuracy rate of 98.37%, which is on average 3.57% better then existing methods.
Keywords
computer games, gesture recognition, image classification, learning (artificial intelligence), patient treatment, random processes, support vector machines, Microsoft Research Cambridge-12 Kinect dataset, adaptive game development, automatic gesture recognition, brute-force classification strategy, brute-force machine learning, dynamic gesture recognition, exergaming, human gesture classification, leave-one-subject-out cross-validation, online continuous human gesture recognition, physiotherapy, random forests, self-captured stealth game gesture dataset, support vector machines, temporal dimension, Decision trees, Games, Gesture recognition, Radio frequency, Skeleton, Training, Vegetation

Downloads

  • 07860414.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 829.80 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Deboeverie, Francis, Sanne Roegiers, Gianni Allebosch, Peter Veelaert, and Wilfried Philips. 2017. “Human Gesture Classification by Brute-force Machine Learning for Exergaming in Physiotherapy.” In 2016 IEEE Conference on Computational Intelligence and Games (CIG), 1–7. IEEE.
APA
Deboeverie, F., Roegiers, S., Allebosch, G., Veelaert, P., & Philips, W. (2017). Human gesture classification by brute-force machine learning for exergaming in physiotherapy. 2016 IEEE Conference on Computational Intelligence and Games (CIG) (pp. 1–7). Presented at the 2016 IEEE Conference on Computational Intelligence and Games (CIG), IEEE.
Vancouver
1.
Deboeverie F, Roegiers S, Allebosch G, Veelaert P, Philips W. Human gesture classification by brute-force machine learning for exergaming in physiotherapy. 2016 IEEE Conference on Computational Intelligence and Games (CIG). IEEE; 2017. p. 1–7.
MLA
Deboeverie, Francis, Sanne Roegiers, Gianni Allebosch, et al. “Human Gesture Classification by Brute-force Machine Learning for Exergaming in Physiotherapy.” 2016 IEEE Conference on Computational Intelligence and Games (CIG). IEEE, 2017. 1–7. Print.
@inproceedings{8525974,
  abstract     = {In this paper, a novel approach for human gesture classification on skeletal data is proposed for the application of exergaming in physiotherapy. Unlike existing methods, we propose to use a general classifier like Random Forests to recognize dynamic gestures. The temporal dimension is handled afterwards by majority voting in a sliding window over the consecutive predictions of the classifier. The gestures can have partially similar postures, such that the classifier will decide on the dissimilar postures. This brute-force classification strategy is permitted, because dynamic human gestures show sufficient dissimilar postures. Online continuous human gesture recognition can classify dynamic gestures in an early stage, which is a crucial advantage when controlling a game by automatic gesture recognition. Also, ground truth can be easily obtained, since all postures in a gesture get the same label, without any discretization into consecutive postures. This way, new gestures can be easily added, which is advantageous in adaptive game development. We evaluate our strategy by a leave-one-subject-out cross-validation on a self-captured stealth game gesture dataset and the publicly available Microsoft Research Cambridge-12 Kinect (MSRC-12) dataset. On the first dataset we achieve an excellent accuracy rate of 96.72\%. Furthermore, we show that Random Forests perform better than Support Vector Machines. On the second dataset we achieve an accuracy rate of 98.37\%, which is on average 3.57\% better then existing methods.},
  author       = {Deboeverie, Francis and Roegiers, Sanne and Allebosch, Gianni and Veelaert, Peter and Philips, Wilfried},
  booktitle    = {2016 IEEE Conference on Computational Intelligence and Games (CIG)},
  isbn         = {978-1-5090-1883-3},
  issn         = {2325-4289},
  keyword      = {computer games,gesture recognition,image classification,learning (artificial intelligence),patient treatment,random processes,support vector machines,Microsoft Research Cambridge-12 Kinect dataset,adaptive game development,automatic gesture recognition,brute-force classification strategy,brute-force machine learning,dynamic gesture recognition,exergaming,human gesture classification,leave-one-subject-out cross-validation,online continuous human gesture recognition,physiotherapy,random forests,self-captured stealth game gesture dataset,support vector machines,temporal dimension,Decision trees,Games,Gesture recognition,Radio frequency,Skeleton,Training,Vegetation},
  language     = {eng},
  location     = {Santorini, Greece},
  pages        = {1--7},
  publisher    = {IEEE},
  title        = {Human gesture classification by brute-force machine learning for exergaming in physiotherapy},
  url          = {http://dx.doi.org/10.1109/cig.2016.7860414},
  year         = {2017},
}

Altmetric
View in Altmetric