DocumentCode :
3419738
Title :
Fuzzy Qualitative Gaussian Inference: Finding hidden Probability Distributions using Fuzzy Membership Functions
Author :
Khoury, Mehdi ; Liu, Honghai
Author_Institution :
Inst. of Ind. Res., Univ. of Portsmouth, Portsmouth
fYear :
2009
fDate :
March 30 2009-April 2 2009
Firstpage :
12
Lastpage :
18
Abstract :
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.
Keywords :
Gaussian distribution; fuzzy set theory; inference mechanisms; pattern classification; fuzzy membership functions; fuzzy qualitative Gaussian inference; hidden probability distributions; natural human motion capture data; Biological system modeling; Biomechanics; Hidden Markov models; Humans; Joints; Machine learning; Motion analysis; Neural networks; Probability distribution; Skeleton;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotic Intelligence in Informationally Structured Space, 2009. RIISS '09. IEEE Workshop on
Conference_Location :
Nashville, TN
Print_ISBN :
978-1-4244-2753-6
Type :
conf
DOI :
10.1109/RIISS.2009.4937900
Filename :
4937900
Link To Document :
بازگشت