Human action recognition using continuous hmms and hog/hof silhouette representation

Mohamed Ibn Khedher, Mounim A. El-Yacoubi, Bernadette Dorizzi

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

Abstract

This paper presents an alternative to the mainstream approach of STIP-based SVM recognition for human recognition. First, it studies whether or not whole silhouette representation by Histogram-of-Oriented- Gradients (HOG) or Histogram-of-Optical-Flow (HOF) descriptors is more discriminated when compared to sparse spatio-temporal interest points (STIPs). Second, it investigates whether explicitly modeling the temporal order of features using continuous HMMs outperforms the standard Bag-of-Words (BoW) representation that overlooks such an order. When both whole silhouette representation and temporal order modeling are combined, a significant improvement is shown on the Weizmann database over STIP-based SVM recognition.

Original languageEnglish
Title of host publicationICPRAM 2012 - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods
Pages503-508
Number of pages6
Publication statusPublished - 18 Jun 2012
Externally publishedYes
Event1st International Conference on Pattern Recognition Applications and Methods, ICPRAM 2012 - Vilamoura, Algarve, Portugal
Duration: 6 Feb 20128 Feb 2012

Publication series

NameICPRAM 2012 - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods
Volume2

Conference

Conference1st International Conference on Pattern Recognition Applications and Methods, ICPRAM 2012
Country/TerritoryPortugal
CityVilamoura, Algarve
Period6/02/128/02/12

Keywords

  • Action recognition
  • Feature discriminative power
  • Temporal correlation

Fingerprint

Dive into the research topics of 'Human action recognition using continuous hmms and hog/hof silhouette representation'. Together they form a unique fingerprint.

Cite this