Adaboost-based algorithm for human action recognition

Nabil Zerrouki; Fouzi Harrou; Ying Sun; Amrane Houacine

doi:10.1109/INDIN.2017.8104769

Adaboost-based algorithm for human action recognition

Nabil Zerrouki, Fouzi Harrou, Ying Sun, Amrane Houacine

Computer, Electrical and Mathematical Sciences and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 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 language	English (US)
Title of host publication	Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	189-193
Number of pages	5
ISBN (Electronic)	9781538608371
DOIs	https://doi.org/10.1109/INDIN.2017.8104769
State	Published - Nov 10 2017
Event	15th IEEE International Conference on Industrial Informatics, INDIN 2017 - Emden, Germany Duration: Jul 24 2017 → Jul 26 2017

Publication series

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

Conference

Conference	15th IEEE International Conference on Industrial Informatics, INDIN 2017
Country/Territory	Germany
City	Emden
Period	07/24/17 → 07/26/17

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

Access to Document

10.1109/INDIN.2017.8104769

Cite this

Zerrouki, N., Harrou, F., Sun, Y., & Houacine, A. (2017). Adaboost-based algorithm for human action recognition. In Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017 (pp. 189-193). Article 8104769 (Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INDIN.2017.8104769

Zerrouki, Nabil ; Harrou, Fouzi ; Sun, Ying et al. / Adaboost-based algorithm for human action recognition. Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 189-193 (Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017).

@inproceedings{cc137e75ea1847afb641e065f5aedf27,

title = "Adaboost-based algorithm for human action recognition",

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.",

author = "Nabil Zerrouki and Fouzi Harrou and Ying Sun and Amrane Houacine",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 15th IEEE International Conference on Industrial Informatics, INDIN 2017 ; Conference date: 24-07-2017 Through 26-07-2017",

year = "2017",

month = nov,

day = "10",

doi = "10.1109/INDIN.2017.8104769",

language = "English (US)",

series = "Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "189--193",

booktitle = "Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017",

address = "United States",

}

Zerrouki, N, Harrou, F , Sun, Y & Houacine, A 2017, Adaboost-based algorithm for human action recognition. in Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017., 8104769, Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017, Institute of Electrical and Electronics Engineers Inc., pp. 189-193, 15th IEEE International Conference on Industrial Informatics, INDIN 2017, Emden, Germany, 07/24/17. https://doi.org/10.1109/INDIN.2017.8104769

Adaboost-based algorithm for human action recognition. / Zerrouki, Nabil; Harrou, Fouzi ; Sun, Ying et al.
Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 189-193 8104769 (Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Adaboost-based algorithm for human action recognition

AU - Zerrouki, Nabil

AU - Harrou, Fouzi

AU - Sun, Ying

AU - Houacine, Amrane

PY - 2017/11/10

Y1 - 2017/11/10

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85041167687&partnerID=8YFLogxK

U2 - 10.1109/INDIN.2017.8104769

DO - 10.1109/INDIN.2017.8104769

M3 - Conference contribution

AN - SCOPUS:85041167687

T3 - Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017

SP - 189

EP - 193

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE International Conference on Industrial Informatics, INDIN 2017

Y2 - 24 July 2017 through 26 July 2017

ER -

Zerrouki N, Harrou F , Sun Y, Houacine A. Adaboost-based algorithm for human action recognition. In Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 189-193. 8104769. (Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017). doi: 10.1109/INDIN.2017.8104769

Adaboost-based algorithm for human action recognition

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this