Low Latency Action Recognition with Depth Information

Ali Seydi Keceli, Ahmet Burak Can

Abstract

In this study an approach for low latency action recognition is proposed. Low latency action recognition aims to recognize actions without observing the whole action sequence. In the proposed approach, a skeletal model is obtained from depth images. Features extracted from the skeletal model are considered as time series and histograms. To classify actions, Adaboost M1 classifier is utilized with an SVM kernel. The trained classifiers are tested with different action observation ratios and compared with some of the studies in the literature. The model produces promising results without observing the whole action sequence.

References

  1. Alpaydin, E., 2004. Introduction to Machine Learning (Adaptive Computation and Machine Learning), The MIT Press.
  2. Altman, N., 1992. An introduction to kernel and nearestneighbor nonparametric regression. The American Statistician, 46(3), p.175-185.
  3. Ellis, C. et al., 2013. Exploring the trade-off between accuracy and observational latency in action recognition. International Journal of Computer Vision, 101(3), p.420-436.
  4. Fothergill, S. et al., 2012. Instructing people for training gestural interactive systems. In Proceedings of the 2012 ACM annual conference on Human Factors in Computing Systems - CHI 7812. ACM Press, pp. 1737- 1746.
  5. Freund, Yoav, Robert Schapire, and N. Abe. 1999. "A short introduction to boosting."Journal-Japanese Society For Artificial Intelligence 14.771-780, 1612.
  6. Hoai, M. & De La Torre, F., 2014. Max-margin early event detectors.International Journal of Computer Vision, 107(2), p.191-202.
  7. Juhl Jensen, L. & Bateman, A., 2011. The Rise and Fall of supervised machine learning techniques. Bioinformatics, 27, p.3331-3332.
  8. Keceli A. S., Can A. B., 2014. Recognition of Basic Human Actions Using Depth Information, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 28, No. 02.
  9. Khushaba, R. N., Al-Jumaily, A. & Al-Ani, A., 2007. Novel feature extraction method based on fuzzy entropy and wavelet packet transform for myoelectric Control. 2007 International Symposium on Communications and Information Technologies.
  10. Li, X., Wang, L. & Sung, E., 2008. AdaBoost with SVMbased component classifiers. Engineering Applications of Artificial Intelligence, 21(5), p.785-795.
  11. Li, W., Zhang, Z. & Liu, Z., 2010. Action recognition based on a bag of 3D points. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010. pp. 9-14.
  12. Liaw, A. & Wiener, M., 2002. Classification and Regression by randomForest. R news, 2, p.18-22.
  13. Shotton, J. et al., 2013. Real-time human pose recognition in parts from single depth images. Studies in Computational Intelligence, 411, p.119-135.
  14. Wang, J. et al., 2012. Mining actionlet ensemble for action recognition with depth cameras. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 1290-1297.
  15. Yang, X. & Tian, Y., 2012. EigenJoints-based action recognition using Naive-Bayes-Nearest-Neighbor. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on. pp. 14-19.
  16. Zanfir, M., Leordeanu, M. & Sminchisescu, C., 2013. The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection. In Computer Vision (ICCV), 2013 IEEE International Conference on. pp. 2752-2759.
Download


Paper Citation


in Harvard Style

Keceli A. and Can A. (2016). Low Latency Action Recognition with Depth Information . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 590-596. DOI: 10.5220/0005723005900596


in Bibtex Style

@conference{visapp16,
author={Ali Seydi Keceli and Ahmet Burak Can},
title={Low Latency Action Recognition with Depth Information},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={590-596},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005723005900596},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - Low Latency Action Recognition with Depth Information
SN - 978-989-758-175-5
AU - Keceli A.
AU - Can A.
PY - 2016
SP - 590
EP - 596
DO - 10.5220/0005723005900596