Title :
Robust Dimensionality Reduction for Human Action Recognition
Author :
Concha, Oscar Perez ; Xu, Richard Yi Da ; Piccardi, Massimo
Author_Institution :
Sch. of Comput. & Commun., Univ. of Technol., Broadway, NSW, Australia
Abstract :
Human action recognition can be approached by combining an action-discriminative feature set with a classifier. However, the dimensionality of typical feature sets joint with that of the time dimension often leads to a curse-of-dimensionality situation. Moreover, the measurement of the feature set is subject to sometime severe errors. This paper presents an approach to human action recognition based on robust dimensionality reduction. The observation probabilities of hidden Markov models (HMM) are modelled by mixtures of probabilistic principal components analyzers and mixtures of t-distribution sub-spaces, and compared with conventional Gaussian mixture models. Experimental results on two datasets show that dimensionality reduction helps improve the classification accuracy and that the heavier-tailed t-distribution can help reduce the impact of outliers generated by segmentation errors.
Keywords :
gesture recognition; hidden Markov models; pattern classification; principal component analysis; probability; Gaussian mixture models; action discriminative feature set; curse-of-dimensionality situation; feature sets joint; hidden Markov model; human action recognition; pattern classifier; probabilistic principal components analyzers; robust dimensionality reduction; segmentation errors; t-distribution subspaces; Analytical models; Hidden Markov models; Humans; Leg; Principal component analysis; Probabilistic logic; Training; Action Recognition; Dimensionality Reduction; HMM;
Conference_Titel :
Digital Image Computing: Techniques and Applications (DICTA), 2010 International Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
978-1-4244-8816-2
Electronic_ISBN :
978-0-7695-4271-3
DOI :
10.1109/DICTA.2010.66