Adaboost-based algorithm for human action recognition

Nabil Zerrouki, Fouzi Harrou, Ying Sun, Amrane Houacine

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

3 Scopus citations

Abstract

This paper presents a computer vision-based methodology for human action recognition. First, the shape based pose features are constructed based on area ratios to identify the human silhouette in images. The proposed features are invariance to translation and scaling. Once the human body features are extracted from videos, different human actions are learned individually on the training frames of each class. Then, we apply the Adaboost algorithm for the classification process. We assessed the proposed approach using the UR Fall Detection dataset. In this study six classes of activities are considered namely: walking, standing, bending, lying, squatting, and sitting. Results demonstrate the efficiency of the proposed methodology.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages189-193
Number of pages5
ISBN (Electronic)9781538608371
DOIs
StatePublished - Nov 10 2017
Event15th IEEE International Conference on Industrial Informatics, INDIN 2017 - Emden, Germany
Duration: Jul 24 2017Jul 26 2017

Publication series

NameProceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017

Conference

Conference15th IEEE International Conference on Industrial Informatics, INDIN 2017
Country/TerritoryGermany
CityEmden
Period07/24/1707/26/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

ASJC Scopus subject areas

  • Information Systems and Management
  • Artificial Intelligence
  • Control and Optimization
  • Education
  • Human-Computer Interaction
  • Hardware and Architecture
  • Industrial and Manufacturing Engineering
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Adaboost-based algorithm for human action recognition'. Together they form a unique fingerprint.

Cite this