View-independent human action recognition with Volume Motion Template on single stereo camera

Myung Cheol Roh, Ho Keun Shin, Seong Whan Lee

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

Vision-based human action recognition provides an advanced interface, and research in the field of human action recognition has been actively carried out. However, an environment from dynamic viewpoint, where we can be in any position, any direction, etc., must be considered in our living 3D space. In order to overcome the viewpoint dependency, we propose a Volume Motion Template (VMT) and Projected Motion Template (PMT). The proposed VMT method is an extension of the Motion History Image (MHI) method to 3D space. The PMT is generated by projecting the VMT into a 2D plane that is orthogonal to an optimal virtual viewpoint where the optimal virtual viewpoint is a viewpoint from which an action can be described in greatest detail, in 2D space. From the proposed method, any actions taken from different viewpoints can be recognized independent of the viewpoints. The experimental results demonstrate the accuracies and effectiveness of the proposed VMT method for view-independent human action recognition.

Original languageEnglish
Pages (from-to)639-647
Number of pages9
JournalPattern Recognition Letters
Volume31
Issue number7
DOIs
Publication statusPublished - 2010 May 1

Fingerprint

Cameras

Keywords

  • Human action recognition
  • Motion History Image
  • View-independence
  • Volume Motion Template

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

View-independent human action recognition with Volume Motion Template on single stereo camera. / Roh, Myung Cheol; Shin, Ho Keun; Lee, Seong Whan.

In: Pattern Recognition Letters, Vol. 31, No. 7, 01.05.2010, p. 639-647.

Research output: Contribution to journalArticle

@article{87c05cdee8af492b82ae6d98efc3d68d,
title = "View-independent human action recognition with Volume Motion Template on single stereo camera",
abstract = "Vision-based human action recognition provides an advanced interface, and research in the field of human action recognition has been actively carried out. However, an environment from dynamic viewpoint, where we can be in any position, any direction, etc., must be considered in our living 3D space. In order to overcome the viewpoint dependency, we propose a Volume Motion Template (VMT) and Projected Motion Template (PMT). The proposed VMT method is an extension of the Motion History Image (MHI) method to 3D space. The PMT is generated by projecting the VMT into a 2D plane that is orthogonal to an optimal virtual viewpoint where the optimal virtual viewpoint is a viewpoint from which an action can be described in greatest detail, in 2D space. From the proposed method, any actions taken from different viewpoints can be recognized independent of the viewpoints. The experimental results demonstrate the accuracies and effectiveness of the proposed VMT method for view-independent human action recognition.",
keywords = "Human action recognition, Motion History Image, View-independence, Volume Motion Template",
author = "Roh, {Myung Cheol} and Shin, {Ho Keun} and Lee, {Seong Whan}",
year = "2010",
month = "5",
day = "1",
doi = "10.1016/j.patrec.2009.11.017",
language = "English",
volume = "31",
pages = "639--647",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "7",

}

TY - JOUR

T1 - View-independent human action recognition with Volume Motion Template on single stereo camera

AU - Roh, Myung Cheol

AU - Shin, Ho Keun

AU - Lee, Seong Whan

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Vision-based human action recognition provides an advanced interface, and research in the field of human action recognition has been actively carried out. However, an environment from dynamic viewpoint, where we can be in any position, any direction, etc., must be considered in our living 3D space. In order to overcome the viewpoint dependency, we propose a Volume Motion Template (VMT) and Projected Motion Template (PMT). The proposed VMT method is an extension of the Motion History Image (MHI) method to 3D space. The PMT is generated by projecting the VMT into a 2D plane that is orthogonal to an optimal virtual viewpoint where the optimal virtual viewpoint is a viewpoint from which an action can be described in greatest detail, in 2D space. From the proposed method, any actions taken from different viewpoints can be recognized independent of the viewpoints. The experimental results demonstrate the accuracies and effectiveness of the proposed VMT method for view-independent human action recognition.

AB - Vision-based human action recognition provides an advanced interface, and research in the field of human action recognition has been actively carried out. However, an environment from dynamic viewpoint, where we can be in any position, any direction, etc., must be considered in our living 3D space. In order to overcome the viewpoint dependency, we propose a Volume Motion Template (VMT) and Projected Motion Template (PMT). The proposed VMT method is an extension of the Motion History Image (MHI) method to 3D space. The PMT is generated by projecting the VMT into a 2D plane that is orthogonal to an optimal virtual viewpoint where the optimal virtual viewpoint is a viewpoint from which an action can be described in greatest detail, in 2D space. From the proposed method, any actions taken from different viewpoints can be recognized independent of the viewpoints. The experimental results demonstrate the accuracies and effectiveness of the proposed VMT method for view-independent human action recognition.

KW - Human action recognition

KW - Motion History Image

KW - View-independence

KW - Volume Motion Template

UR - http://www.scopus.com/inward/record.url?scp=77649337452&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649337452&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2009.11.017

DO - 10.1016/j.patrec.2009.11.017

M3 - Article

AN - SCOPUS:77649337452

VL - 31

SP - 639

EP - 647

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 7

ER -