IEEE Computer Graphics and Applications
Evaluation of the CyberGlove as a whole-hand input device
ACM Transactions on Computer-Human Interaction (TOCHI)
Automated Derivation of Primitives for Movement Classification
Autonomous Robots
An Online Algorithm for Segmenting Time Series
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
A survey on vision-based human action recognition
Image and Vision Computing
Online Segmentation of Time Series Based on Polynomial Least-Squares Approximations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Joint segmentation and classification of time series using class-specific features
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Using SVD for Segmentation and Classification of Human Hand Actions
ICMLA '11 Proceedings of the 2011 10th International Conference on Machine Learning and Applications and Workshops - Volume 01
Hi-index | 0.00 |
The development of a system for classifying and interpreting human hands motion is considered in this paper. This is obtained by locally approximating motion data with rank-1 structures. The approximation is obtained in two steps: first the time series is decomposed into simpler sub-series (segmentation), then each subseries labelled by a unique vector. The effectiveness of the proposed strategy is shown on sensory data from a data-glove when a human picks a tin can and a pencil. The strategy proves to be simple and reliable, even in the presence of unknown data corrupted by noise, and can be used as a basis for real-time automated recognition and interpretation of human gesture.