Pentagon profile as image representation for human action interpretation task

Farah Yasmin Abdul Rahman, Aini Hussain, Nooritawati Md Tahir, Mohamad Hanif Md Saad

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

1 Citation (Scopus)

Abstract

The emergence of various vision-based applications has led researchers to do research on human action recognition. Good feature extraction technique is one of the important factors in making an efficient action recognition system. In this work, we propose a technique which we called 'pentagon profile' to represent the image for the human action interpretation task. This profile is generated by connecting the points detected at the human head, hand and feet of a human silhouette image. These points when connected form a unique shape with five-sided polygons that prompt the name pentagon profile. Initial finding shows that this feature extraction technique gives promising result to represent the human activity especially in standing and squatting posture.

Original languageEnglish
Title of host publicationProceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011
Pages377-381
Number of pages5
DOIs
Publication statusPublished - 2011
Event2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011 - Penang
Duration: 4 Mar 20116 Mar 2011

Other

Other2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011
CityPenang
Period4/3/116/3/11

Fingerprint

Feature extraction

Keywords

  • Feature extraction
  • human action representation
  • pentagon profile

ASJC Scopus subject areas

  • Signal Processing

Cite this

Abdul Rahman, F. Y., Hussain, A., Md Tahir, N., & Md Saad, M. H. (2011). Pentagon profile as image representation for human action interpretation task. In Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011 (pp. 377-381). [5759906] https://doi.org/10.1109/CSPA.2011.5759906

Pentagon profile as image representation for human action interpretation task. / Abdul Rahman, Farah Yasmin; Hussain, Aini; Md Tahir, Nooritawati; Md Saad, Mohamad Hanif.

Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011. 2011. p. 377-381 5759906.

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

Abdul Rahman, FY, Hussain, A, Md Tahir, N & Md Saad, MH 2011, Pentagon profile as image representation for human action interpretation task. in Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011., 5759906, pp. 377-381, 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011, Penang, 4/3/11. https://doi.org/10.1109/CSPA.2011.5759906
Abdul Rahman FY, Hussain A, Md Tahir N, Md Saad MH. Pentagon profile as image representation for human action interpretation task. In Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011. 2011. p. 377-381. 5759906 https://doi.org/10.1109/CSPA.2011.5759906
Abdul Rahman, Farah Yasmin ; Hussain, Aini ; Md Tahir, Nooritawati ; Md Saad, Mohamad Hanif. / Pentagon profile as image representation for human action interpretation task. Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011. 2011. pp. 377-381
@inproceedings{d72bd6f955b44b7bbe660e21afbfd92f,
title = "Pentagon profile as image representation for human action interpretation task",
abstract = "The emergence of various vision-based applications has led researchers to do research on human action recognition. Good feature extraction technique is one of the important factors in making an efficient action recognition system. In this work, we propose a technique which we called 'pentagon profile' to represent the image for the human action interpretation task. This profile is generated by connecting the points detected at the human head, hand and feet of a human silhouette image. These points when connected form a unique shape with five-sided polygons that prompt the name pentagon profile. Initial finding shows that this feature extraction technique gives promising result to represent the human activity especially in standing and squatting posture.",
keywords = "Feature extraction, human action representation, pentagon profile",
author = "{Abdul Rahman}, {Farah Yasmin} and Aini Hussain and {Md Tahir}, Nooritawati and {Md Saad}, {Mohamad Hanif}",
year = "2011",
doi = "10.1109/CSPA.2011.5759906",
language = "English",
isbn = "9781612844145",
pages = "377--381",
booktitle = "Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011",

}

TY - GEN

T1 - Pentagon profile as image representation for human action interpretation task

AU - Abdul Rahman, Farah Yasmin

AU - Hussain, Aini

AU - Md Tahir, Nooritawati

AU - Md Saad, Mohamad Hanif

PY - 2011

Y1 - 2011

N2 - The emergence of various vision-based applications has led researchers to do research on human action recognition. Good feature extraction technique is one of the important factors in making an efficient action recognition system. In this work, we propose a technique which we called 'pentagon profile' to represent the image for the human action interpretation task. This profile is generated by connecting the points detected at the human head, hand and feet of a human silhouette image. These points when connected form a unique shape with five-sided polygons that prompt the name pentagon profile. Initial finding shows that this feature extraction technique gives promising result to represent the human activity especially in standing and squatting posture.

AB - The emergence of various vision-based applications has led researchers to do research on human action recognition. Good feature extraction technique is one of the important factors in making an efficient action recognition system. In this work, we propose a technique which we called 'pentagon profile' to represent the image for the human action interpretation task. This profile is generated by connecting the points detected at the human head, hand and feet of a human silhouette image. These points when connected form a unique shape with five-sided polygons that prompt the name pentagon profile. Initial finding shows that this feature extraction technique gives promising result to represent the human activity especially in standing and squatting posture.

KW - Feature extraction

KW - human action representation

KW - pentagon profile

UR - http://www.scopus.com/inward/record.url?scp=79957458618&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957458618&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2011.5759906

DO - 10.1109/CSPA.2011.5759906

M3 - Conference contribution

AN - SCOPUS:79957458618

SN - 9781612844145

SP - 377

EP - 381

BT - Proceedings - 2011 IEEE 7th International Colloquium on Signal Processing and Its Applications, CSPA 2011

ER -