Robust multi-modal group action recognition in meetings from disturbed videos with the asynchronous Hidden Markov model

Marc Al-Hames, Claus Lenz, Stephan Reiter, Joachim Schenk, Frank Wallhoff, Gerhard Rigoll

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

The Asynchronous Hidden Markov Model (AHMM) models the joint likelihood of two observation sequences, even if the streams are not synchronised. We explain this concept and how the model is trained by the EM algorithm. We then show how the AHMM can be applied to the analysis of group action events in meetings from both clear and disturbed data. The AHMM outperforms an early fusion HMM by 5.7% recognition rate (a rel. error reduction of 38.5%) for clear data. For occluded data, the improvement is in average 6.5% recognition rate (rel. error red. 40%). Thus asynchronity is a dominant factor in meeting analysis, even if the data is disturbed. The AHMM exploits this and is therefore much more robust against disturbances.

Original languageEnglish
Title of host publication2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
PagesII213-II216
DOIs
StatePublished - 2007
Event14th IEEE International Conference on Image Processing, ICIP 2007 - San Antonio, TX, United States
Duration: 16 Sep 200719 Sep 2007

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2
ISSN (Print)1522-4880

Conference

Conference14th IEEE International Conference on Image Processing, ICIP 2007
Country/TerritoryUnited States
CitySan Antonio, TX
Period16/09/0719/09/07

Keywords

  • Hidden Markov models
  • Meetings
  • Multimedia communication
  • Robustness
  • Video signal processing

Fingerprint

Dive into the research topics of 'Robust multi-modal group action recognition in meetings from disturbed videos with the asynchronous Hidden Markov model'. Together they form a unique fingerprint.

Cite this