Silhouette history and energy image information for human movement recognition

Mohiuddin Ahmad, Irine Parvin, Seong Whan Lee

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

In this paper, we propose spatio-temporal silhouette representations, called silhouette energy image (SEI) and silhouette history image (SHI) to characterize motion and shape properties for recognition of human movements such as human actions, activities in daily life. The SEI and SHI are constructed by using the silhouette image sequence of an action. The span or difference of the end time and start time is used to make the SHI. For addressing the human shape variability, we used the variation of the anthropometry of the person. We extract the features based on geometric shape moments. We tested our approach successfully in the indoor and outdoor environment. Our experimental results show that the proposed method of human action recognition is robust, flexible and efficient.

Original languageEnglish
Pages (from-to)12-21
Number of pages10
JournalJournal of Multimedia
Volume5
Issue number1
DOIs
Publication statusPublished - 2010 Feb 17

Fingerprint

Anthropometry

Keywords

  • Anthropometry
  • Human action recognition
  • Shape variability
  • Silhouette energy image
  • Silhouette history image

ASJC Scopus subject areas

  • Artificial Intelligence
  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Silhouette history and energy image information for human movement recognition. / Ahmad, Mohiuddin; Parvin, Irine; Lee, Seong Whan.

In: Journal of Multimedia, Vol. 5, No. 1, 17.02.2010, p. 12-21.

Research output: Contribution to journalArticle

@article{de78cd1930bf41d19897b781b6d6250a,
title = "Silhouette history and energy image information for human movement recognition",
abstract = "In this paper, we propose spatio-temporal silhouette representations, called silhouette energy image (SEI) and silhouette history image (SHI) to characterize motion and shape properties for recognition of human movements such as human actions, activities in daily life. The SEI and SHI are constructed by using the silhouette image sequence of an action. The span or difference of the end time and start time is used to make the SHI. For addressing the human shape variability, we used the variation of the anthropometry of the person. We extract the features based on geometric shape moments. We tested our approach successfully in the indoor and outdoor environment. Our experimental results show that the proposed method of human action recognition is robust, flexible and efficient.",
keywords = "Anthropometry, Human action recognition, Shape variability, Silhouette energy image, Silhouette history image",
author = "Mohiuddin Ahmad and Irine Parvin and Lee, {Seong Whan}",
year = "2010",
month = "2",
day = "17",
doi = "10.4304/jmm.5.1",
language = "English",
volume = "5",
pages = "12--21",
journal = "Journal of Multimedia",
issn = "1796-2048",
publisher = "Academy Publisher",
number = "1",

}

TY - JOUR

T1 - Silhouette history and energy image information for human movement recognition

AU - Ahmad, Mohiuddin

AU - Parvin, Irine

AU - Lee, Seong Whan

PY - 2010/2/17

Y1 - 2010/2/17

N2 - In this paper, we propose spatio-temporal silhouette representations, called silhouette energy image (SEI) and silhouette history image (SHI) to characterize motion and shape properties for recognition of human movements such as human actions, activities in daily life. The SEI and SHI are constructed by using the silhouette image sequence of an action. The span or difference of the end time and start time is used to make the SHI. For addressing the human shape variability, we used the variation of the anthropometry of the person. We extract the features based on geometric shape moments. We tested our approach successfully in the indoor and outdoor environment. Our experimental results show that the proposed method of human action recognition is robust, flexible and efficient.

AB - In this paper, we propose spatio-temporal silhouette representations, called silhouette energy image (SEI) and silhouette history image (SHI) to characterize motion and shape properties for recognition of human movements such as human actions, activities in daily life. The SEI and SHI are constructed by using the silhouette image sequence of an action. The span or difference of the end time and start time is used to make the SHI. For addressing the human shape variability, we used the variation of the anthropometry of the person. We extract the features based on geometric shape moments. We tested our approach successfully in the indoor and outdoor environment. Our experimental results show that the proposed method of human action recognition is robust, flexible and efficient.

KW - Anthropometry

KW - Human action recognition

KW - Shape variability

KW - Silhouette energy image

KW - Silhouette history image

UR - http://www.scopus.com/inward/record.url?scp=78651593164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651593164&partnerID=8YFLogxK

U2 - 10.4304/jmm.5.1

DO - 10.4304/jmm.5.1

M3 - Article

AN - SCOPUS:78651593164

VL - 5

SP - 12

EP - 21

JO - Journal of Multimedia

JF - Journal of Multimedia

SN - 1796-2048

IS - 1

ER -