An improved clustering for action recognition in online video

Author

Huang, Shenglan ; Chu, Yunxia ; Zhang, Jun

Author_Institution

Shijiazhuang Vocational Technol. Inst., Shijiazhuang, China

fYear

2011

fDate

26-28 July 2011

Firstpage

180

Lastpage

183

Abstract

A new method for human action recognition in online video sequences using Latent Dirichlet Markov Clustering (LDMC) is proposed. Video sequences are represented by a novel "bag-of-words" representation, and each frame corresponds to a "word". LDMC builds on Hidden Markov Models (HMMs) and Latent Dirichlet Allocation, and it overcome their low recognition rate, robustness and high computational complexity. A collapsed Gibbs sampler is designed for offline learning with unlabeled training data, and a new approximation to online Bayesian inference is formulated to enable human action recognition in new online video sequence in real-time. The strength of this model is demonstrated by unsupervised learning of human action categories and detecting salient actions in one complex and crowded public scenes.

Keywords

belief networks; hidden Markov models; image motion analysis; image recognition; unsupervised learning; video signal processing; bag-of-words representation; collapsed Gibbs sampler; computational complexity; crowded public scenes; hidden Markov models; human action recognition; latent Dirichlet Markov clustering; latent Dirichlet allocation; offline learning; online Bayesian inference; online video sequences; salient action; unlabeled training data; unsupervised learning; Bayesian methods; Computational modeling; Hidden Markov models; Humans; Markov processes; Video sequences; Visualization; Bayesian Topic Models; Computer Vision; Hidden Markov Model; Latent Dirichlet Allocation;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Technology (ICMT), 2011 International Conference on

Conference_Location

Hangzhou

Print_ISBN

978-1-61284-771-9

Type

conf

DOI

10.1109/ICMT.2011.6001895

Filename

6001895