Human action recognition based on two-view optical flow in the transformed domain

Mohamed A. Abdelwahab, Moataz M. Abdelwahab

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper a human action recognition algorithm based on two-view of optical flow in multiple layers per camera employing the transform domain and 2DPCA is presented. This method explores more distinctive features between actions. It is not sensitive to translation, alignment and noise. In addition the use of 2DPCA maintains the spatial relation between pixels and increases the recognition accuracy. Experimental results performed on the Weizmann and IXMAS datasets confirm these excellent properties compared to recent reported methods.

Original languageEnglish
Title of host publication2014 IEEE 57th International Midwest Symposium on Circuits and Systems, MWSCAS 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages805-808
Number of pages4
ISBN (Electronic)9781479941346, 9781479941346
DOIs
Publication statusPublished - Sept 23 2014
Externally publishedYes
Event2014 IEEE 57th International Midwest Symposium on Circuits and Systems, MWSCAS 2014 - College Station, United States
Duration: Aug 3 2014Aug 6 2014

Publication series

NameMidwest Symposium on Circuits and Systems
ISSN (Print)1548-3746

Conference

Conference2014 IEEE 57th International Midwest Symposium on Circuits and Systems, MWSCAS 2014
Country/TerritoryUnited States
CityCollege Station
Period8/3/148/6/14

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Human action recognition based on two-view optical flow in the transformed domain'. Together they form a unique fingerprint.

Cite this