Fuzzy Qualitative Gaussian Inference: Finding hidden Probability Distributions using Fuzzy Membership Functions

This paper introduces Fuzzy Qualitative Gaussian Inference: a novel way to build Fuzzy Membership Functions that map to hidden Probability Distributions underlying the informationally structured space. This method is used to classify boxing moves from natural human Motion Capture data. In our experiment, the system is able to recognise seven different boxing stances simultaneously with an accuracy superior to a GMM-based classifier. Results seem to indicate that a template can be learned and a stance identified in under 18 milliseconds, which may allow recognition in real-time.

[1]  Bohdan S. Butkiewicz,et al.  A Method for Automatic Membership Function Estimation Based on Fuzzy Measures , 2007, IFSA.

[2]  Shweta Sanghi,et al.  Determining the membership values to optimize retrieval in a fuzzy relational database , 2006, ACM-SE 44.

[3]  Fazel Naghdy,et al.  Human Motion Recognition through Fuzzy Hidden Markov Model , 2005, International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06).

[4]  Dan Simon,et al.  Hinfinity estimation for fuzzy membership function optimization , 2005, Int. J. Approx. Reason..

[5]  Bryan Buchholz,et al.  ISB recommendation on definitions of joint coordinate systems of various joints for the reporting of human joint motion--Part II: shoulder, elbow, wrist and hand. , 2005, Journal of biomechanics.

[6]  Tieniu Tan,et al.  Recent developments in human motion analysis , 2003, Pattern Recognit..

[7]  Hartmut Witte,et al.  ISB recommendation on definitions of joint coordinate system of various joints for the reporting of human joint motion--part I: ankle, hip, and spine. International Society of Biomechanics. , 2002, Journal of biomechanics.

[8]  N. Crawford.  A sequence of two rotations--50 degrees torso flexion followed by +/-120 degrees of head axial rotation--was monitored using (essentially) goniometers and simultaneously measured by Euler XZY an YZX decompositions of marker data from an electromagnetic system (Flock of Birds). , 2002, Clinical biomechanics.

[9]  David C. Hogg,et al.  Learning Variable-Length Markov Models of Behavior , 2001, Comput. Vis. Image Underst..

[10]  Chin-Teng Lin,et al.  A Space-Time Delay Neural Network for Motion Recognition and its Application to Lipreading , 1999, Int. J. Neural Syst..

[11]  G. Yamaguchi,et al.  A new technique for determining 3-D joint angles: the tilt/twist method. , 1999, Clinical biomechanics.

[12]  Michael J. Black,et al.  Parameterized modeling and recognition of activities , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[13]  Tieniu Tan,et al.  Agent orientated annotation in model based visual surveillance , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[14]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Jae-Hoon Kim,et al.  Estimating Membership Functions in a Fuzzy Network Model for Part-of-Speech Tagging , 1996, J. Intell. Fuzzy Syst..

[16]  Aaron F. Bobick,et al.  A state-based technique for the summarization and recognition of gesture , 1995, Proceedings of IEEE International Conference on Computer Vision.

[17]  T. Iokibe.  A method for automatic rule and membership function generation by discretionary fuzzy performance function and its application to a practical system , 1994, NAFIPS/IFIS/NASA '94. Proceedings of the First International Joint Conference of The North American Fuzzy Information Processing Society Biannual Conference. The Industrial Fuzzy Control and Intellige.

[18]  Jake K. Aggarwal,et al.  Articulated and elastic non-rigid motion: a review , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

[19]  Gang Xu,et al.  Understanding human motion patterns , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[20]  B. D. Russell,et al.  Automatic generation of membership function and fuzzy rule using inductive reasoning , 1993, Third International Conference on Industrial Fuzzy Control and Intelligent Systems.

[21]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  V. V. S. Sarma,et al.  Estimation of fuzzy memberships from histograms , 1985, Inf. Sci..

[23]  Honghai Liu,et al.  Recognition of Human Motion From Qualitative Normalised Templates , 2007, J. Intell. Robotic Syst..

[24]  Rachid Aissaoui,et al.  3D joint rotation measurement using MEMs inertial sensors: Application to the knee joint , 2006 .

[25]  Neil D. Lawrence,et al.  MOCAP Toolbox for MATLAB , 2005 .

[26]  Tap Io Frantti,et al.  TIMING OF FUZZY MEMBERSHIP FUNCTIONS FROM DATA , 2001 .