Motion Feature Combination for Human Action Recognition in Video

Hongying Meng, Nick Pears, Chris Bailey

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


We study the human action recognition problem based on motion features directly extracted from video. In order to implement a fast human action recognition system, we select simple features that can be obtained from non-intensive computation. We propose to use the motion history image (MHI) as our fundamental representation of the motion. This is then further processed to give a histogram of the MHI and the Haar wavelet transform of the MHI. The combination of these two features is computed cheaply and has a lower dimension than the original MHI. The combined feature vector is tested in a Support Vector Machine (SVM) based human action recognition system and a significant performance improvement has been achieved. The system is efficient to be used in real-time human action classification systems.

Original languageEnglish
Title of host publicationComputer Vision and Computer Graphics. Theory and Applications
Subtitle of host publicationInternational Conference VISIGRAPH 2007, Barcelona, Spain, March 8-11, 2007. Revised Selected Papers
Number of pages13
ISBN (Electronic)978-3-540-89682-1
ISBN (Print)978-3-540-89681-4
Publication statusPublished - 2009

Publication series

NameCommunications in Computer and Information Science
ISSN (Print)1865-0929

Bibliographical note

Volume is 'Computer Vision and Computer Graphics. Theory and Applications' within series 'Communications in Computer and Information Science' Print ISBN 978-3-540-89681-4; Online ISBN 978-3-540-89682-1; Series ISSN 1865-0929.


  • Event recognition
  • Human action recognition
  • Video analysis
  • Support Vector Machine

Cite this