Estimation of fuzzy memberships from histograms
Information Sciences: an International Journal
A state-based technique for the summarization and recognition of gesture
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Agent Orientated Annotation in Model Based Visual Surveillance
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Parameterized Modeling and Recognition of Activities
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Determining the membership values to optimize retrieval in a fuzzy relational database
Proceedings of the 44th annual Southeast regional conference
Recognition of Human Motion From Qualitative Normalised Templates
Journal of Intelligent and Robotic Systems
Modeling human activity from voxel person using fuzzy logic
IEEE Transactions on Fuzzy Systems
H∞ estimation for fuzzy membership function optimization
International Journal of Approximate Reasoning
A Fuzzy Qualitative Framework for Connecting Robot Qualitative and Quantitative Representations
IEEE Transactions on Fuzzy Systems
| Hi-index | 0.00 |
This paper continues to explore the potential of newly introduced Fuzzy Gaussian Inference (FGI) [1]. It aims at constructing fuzzy membership functions by modelling hidden probability distributions underlying human motions. A fuzzy rule-based system has been employed to assist boxing motion classification from natural human Motion Capture data. In this experiment, FGI alone is able to recognise seven different boxing stances simultaneously with an accuracy superior to a GMM-based classifier. Results indicate that adding a Fuzzy Inference Engine on top of FGI improves the accuracy of the classifier in a consistent way.