Abstract
This paper combines the novel concept of Fuzzy Gaussian Inference(FGI) with Genetic Programming (GP) in order to accurately classify real natural 3d human Motion Capture data. FGI builds Fuzzy Membership Functions that map to hidden Probability Distributions underlying human motions, providing a suitable modelling paradigm for such noisy data. Genetic Programming (GP) is used to make a time dependent and context aware filter that improves the qualitative output of the classifier. Results show that FGI outperforms a GMM-based classifier when recognizing seven different boxing stances simultaneously, and that the addition of the GP based filter improves the accuracy of the FGI classifier significantly.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Aggarwal, J.K., Cai, Q., Liao, W., Sabata, B.: Articulated and elastic non-rigid motion: A review. In: Proc. IEEE Workshop on Motion of Non-Rigid and Articulated Objects, pp. 2–14 (1994)
Anderson, D., Luke, R.H., Keller, J.M., Skubic, M.: Modeling human activity from voxel person using fuzzy logic. IEEE Transactions on Fuzzy Systems (accepted for publication, 2009)
Bobick, A.F., Wilson, A.D.: A state based technique for the summarization and recognition of gesture. In: International Conference on Computer Vision, pp. 382–388 (1995)
Chan, C.S., Liu, H., Brown, D.J.: Recognition of human motion from qualitative normalised templates. Journal of Intelligent and Robotic Systems 48(1), 79–95 (2007)
Chang, C.S., Liu, H.: Fuzzy qualitative human motion analysis. IEEE Transactions on Fuzzy Systems 17(4), 851–862 (2009)
Darby, J., Li, B., Costen, N.: Human activity recognition: Enhancement for gesture based game interfaces. In: 3rd Int. Conf. on Games Research and Development, CyberGames (2007)
Devi, B.B., Sarma, V.V.S.: Estimation of fuzzy memberships from histograms. Inf. Sci. 35(1), 43–59 (1985)
Favre, J., Aissaoui, R., Jolles, B.M., Siegrist, O., de Guise, J.A., Aminian, K.: 3d joint rotation measurement using mems inertial sensors: Application to the knee joint. In: ISB-3D: 3-D Analysis of Human Movement, Valenciennes, France, June 28-30 (2006)
Frantti, T.: Timing of fuzzy membership functions from data. Academic Dissertation - University of Oulu - Finland (July 2001)
Guo, Y., Xu, G., Tsuji, S.: Understanding human motion patterns. In: International Conference on Pattern Recognition, pp. B:325–329 (1994)
Iokibe, T.: A method for automatic rule and membership function generation by discretionary fuzzy performance function and its application to a practical system. In: Proceedings of the First International Joint Conference of the North American Fuzzy Information Processing Society Biannual Conference, pp. 363–364 (1994)
Khoury, M.: pystep or python strongly typed genetic programming, http://pystep.sourceforge.net/
Khoury, M., Liu, H.: Fuzzy qualitative gaussian inference: Finding hidden probability distributions using fuzzy membership functions. In: IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 (2009)
Kim, C., Russell, B.: Automatic generation of membership function and fuzzy rule using inductive reasoning. In: Third International Conference on Industrial Fuzzy Control and Intelligent Systems, 1993. IFIS 1993, pp. 93–96 (1993)
Kim, J., Seo, J., Kim, G.: Estimating membership functions in a fuzzy network model for part-of-speech tagging. Journal of Intelligent and Fuzzy Systems 4, 309–320 (1996)
Lawrence, N.D.: Mocap toolbox for matlab/, http://www.cs.man.ac.uk/~neill/mocap
Liu, H.: A fuzzy qualitative framework for connecting robot qualitative and quantitative representations. IEEE Transactions on Fuzzy Systems 16(8), 1522–1530 (2008)
Liu, H., Brown, D.J., Coghill, G.M.: Fuzzy qualitative robot kinematics. IEEE T. Fuzzy Systems 16(3), 808–822 (2008)
Nieradka, G., Butkiewicz, B.S.: A method for automatic membership function estimation based on fuzzy measures,’. In: Melin, P., Castillo, O., Aguilar, L.T., Kacprzyk, J., Pedrycz, W. (eds.) IFSA 2007. LNCS (LNAI), vol. 4529, pp. 451–460. Springer, Heidelberg (2007)
Pentland, A.P., Oliver, N., Brand, M.: Coupled hidden markov models for complex action recognition. In: Massachusetts Institute of Technology, Media Lab (1996)
Remagnino, P., Tan, T.N., Baker, K.D.: Agent orientated annotation in model based visual surveillance. In: International Conference on Computer Vision, pp. 857–862 (1998)
Sanghi, S.: Determining membership function values to optimize retrieval in a fuzzy relational database. In: Proceedings of the 2006 ACM SE Conference, vol. 1, pp. 537–542 (2006)
Simon, D.: H infinity estimation for fuzzy membership function optimization. Int. J. Approx. Reasoning 40(3), 224–242 (2005)
Thingvold, J.: Biovision bvh format (1999), http://www.cs.wisc.edu/graphics/Courses/cs-838-1999/Jeff
Wang, L., Hu, W., Tan, T.: Recent developments in human motion analysis. Pattern Recognition 36(3), 585–601 (2003)
Yacoob, Y., Black, M.: Parameterized modeling and recognition of activities. In: Sixth International Conference on Computer Vision, 1998, pp. 120–127 (1998)
Yamato, J., Ohya, J., Ishii, K.: Recognizing human action in time-sequential images using hidden markov model. In: IEEE Computer Vision and Pattern Recognition, pp. 379–385 (1992)
Zadeh, L.: Fuzzy sets. Information and Control 8, 338–353 (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Khoury, M., Liu, H. (2009). Classifying 3D Human Motions by Mixing Fuzzy Gaussian Inference with Genetic Programming. In: Xie, M., Xiong, Y., Xiong, C., Liu, H., Hu, Z. (eds) Intelligent Robotics and Applications. ICIRA 2009. Lecture Notes in Computer Science(), vol 5928. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10817-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-10817-4_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10816-7
Online ISBN: 978-3-642-10817-4
eBook Packages: Computer ScienceComputer Science (R0)