Human action recognition using boosted EigenActions

Chang Liu, Pong C. Yuen*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

45 Citations (Scopus)

Abstract

This paper proposes a boosting EigenActions algorithm for human action recognition. A spatio-temporal Information Saliency Map (ISM) is calculated from a video sequence by estimating pixel density function. A continuous human action is segmented into a set of primitive periodic motion cycles from information saliency curve. Each cycle of motion is represented by a Salient Action Unit (SAU), which is used to determine the EigenAction using principle component analysis. A human action classifier is developed using multi-class Adaboost algorithm with Bayesian hypothesis as the weak classifier. Given a human action video sequence, the proposed method effectively locates the SAUs in the video, and recognizes the human actions by categorizing the SAUs. Two publicly available human action databases, namely KTH and Weizmann, are selected for evaluation. The average recognition accuracy are 81.5% and 98.3% for KTH and Weizmann databases, respectively. Comparative results with two recent methods and robustness test results are also reported.

Original languageEnglish
Pages (from-to)825-835
Number of pages11
JournalImage and Vision Computing
Volume28
Issue number5
DOIs
Publication statusPublished - May 2010

Scopus Subject Areas

  • Signal Processing
  • Computer Vision and Pattern Recognition

User-Defined Keywords

  • Adaboost
  • Human action recognition
  • Salient action unit

Fingerprint

Dive into the research topics of 'Human action recognition using boosted EigenActions'. Together they form a unique fingerprint.

Cite this