Multi-view transition HMMs based view-invariant human action recognition method

Xiaofei Ji, Zhaojie Ju, Ce Wang, Changhui Wang

Research output: Contribution to journalArticlepeer-review

203 Downloads (Pure)

Abstract

View-invariant human action recognition is a challenging research topic in computer vision. Hidden Markov Models(HMM) and their extensions have been widely used for view-invariant action recognition. However those methods are usually according to a large parameter space, requiring amounts of training data and with low classification accuracies for real application. A novel graphical structure based on HMM with multi-view transition is proposed to model the human action with viewpoint changing. The model consists of multiple sub action models, which correspond to the traditional HMM utilized to model the human action in a particular rotation viewpoint space. In the training process, the novel model can be built by connecting the sub action models between adjacent viewpoint spaces. In the recognition process, action with unknown viewpoint is recognized by using improved forward algorithm. The proposed model can not only simplify the model training process by decomposing the parameter space into multiple sub-spaces, but also improve the performance the algorithm by constraining the possible viewpoint changing. Experiment results on IXMAS dataset demonstrated that the proposed model obtains better performance than other recent view-invariant action recognition method.
Original languageEnglish
Pages (from-to)11847-11864
JournalMultimedia Tools and Applications
Volume75
Issue number19
Early online date10 May 2015
DOIs
Publication statusPublished - Oct 2016

Keywords

  • wnu

Fingerprint

Dive into the research topics of 'Multi-view transition HMMs based view-invariant human action recognition method'. Together they form a unique fingerprint.

Cite this