Deakin University
Browse

File(s) under permanent embargo

Human action recognition based on 3D SIFT and LDA model

conference contribution
posted on 2011-01-01, 00:00 authored by P Liu, Jin Wang, Fenghua SheFenghua She, H Liu
How to recognize human action from videos captured by modern cameras efficiently and effectively is a challenge in real applications. Traditional methods which need professional analysts are facing a bottleneck because of their shortcomings. To cope with the disadvantage, methods based on computer vision techniques, without or with only a few human interventions, have been proposed to analyse human actions in videos automatically. This paper provides a method combining the three dimensional Scale Invariant Feature Transform (SIFT) detector and the Latent Dirichlet Allocation (LDA) model for human motion analysis. To represent videos effectively and robustly, we extract the 3D SIFT descriptor around each interest point, which is sampled densely from 3D Space-time video volumes. After obtaining the representation of each video frame, the LDA model is adopted to discover the underlying structure-the categorization of human actions in the collection of videos. Public available standard datasets are used to test our method. The concluding part discusses the research challenges and future directions.

History

Event

IEEE Workshop on Robotic Intelligence in Informationally Structured Space (2011 : Paris, France)

Series

IEEE Symposium Series on Computational Intelligence

Pagination

1 - 6

Publisher

IEEE

Location

Paris, France

Place of publication

[Paris, France]

Start date

2011-04-11

End date

2011-04-15

ISBN-13

9781424498857

ISBN-10

1424498856

Language

eng

Publication classification

E2 Full written paper - non-refereed / Abstract reviewed

Copyright notice

2011, IEEE

Title of proceedings

RiiSS 2011 : Proceedings of the 2011 IEEE Workshop on Robotic Intelligence in Informationally Structured Space

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC