RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma

Deniz Gürkaynak; Hülya Yalçin

doi:10.1109/SIU.2015.7130190

RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma

Translated title of the contribution: Recognition and classification of human activity from RGB-D videos

Deniz Gürkaynak, Hülya Yalçin

Department of Mechanical Engineering

Istanbul Technical University

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

3 Citations (Scopus)

Abstract

Human activity recognition has many applications in computer vision, including personal assistive robotics and smart homes/environments. Due to the large temporal and spatial variations in actions performed by humans, human action recognition has been a long-standing challenge. This paper presents a method that recognizes certain human activities based on a motion descriptor that uses 3D human skeleton data. A motion descriptor (SHOJD) is defined using the 3D distance between the most frequent key poses that occur throughout the action that is intended to be recognized. SHOJD features are then fed into an artificial neural network for classification. Experimental results indicate that the SHOJD based human action recognition system is robust with high recognition rate.

Translated title of the contribution	Recognition and classification of human activity from RGB-D videos
Original language	Turkish
Title of host publication	2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1745-1748
Number of pages	4
ISBN (Electronic)	9781467373869
DOIs	https://doi.org/10.1109/SIU.2015.7130190
Publication status	Published - 19 Jun 2015
Event	2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Malatya, Turkey Duration: 16 May 2015 → 19 May 2015

Publication series

Name	2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings

Conference

Conference	2015 23rd Signal Processing and Communications Applications Conference, SIU 2015
Country/Territory	Turkey
City	Malatya
Period	16/05/15 → 19/05/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Access to Document

10.1109/SIU.2015.7130190

Cite this

Gürkaynak, D., & Yalçin, H. (2015). RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma. In 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings (pp. 1745-1748). Article 7130190 (2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU.2015.7130190

Gürkaynak, Deniz ; Yalçin, Hülya. / RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma. 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1745-1748 (2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings).

@inproceedings{aa35687e424f4f20ba60f437505dcc1f,

title = "RGB-D G{\"o}r{\"u}nt{\"u}lerinden Insan Aktivitesi Tanima ve Siniflandirma",

abstract = "Human activity recognition has many applications in computer vision, including personal assistive robotics and smart homes/environments. Due to the large temporal and spatial variations in actions performed by humans, human action recognition has been a long-standing challenge. This paper presents a method that recognizes certain human activities based on a motion descriptor that uses 3D human skeleton data. A motion descriptor (SHOJD) is defined using the 3D distance between the most frequent key poses that occur throughout the action that is intended to be recognized. SHOJD features are then fed into an artificial neural network for classification. Experimental results indicate that the SHOJD based human action recognition system is robust with high recognition rate.",

keywords = "RGB-D imaging, activity recognition, motion descriptors",

author = "Deniz G{\"u}rkaynak and H{\"u}lya Yal{\c c}in",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 ; Conference date: 16-05-2015 Through 19-05-2015",

year = "2015",

month = jun,

day = "19",

doi = "10.1109/SIU.2015.7130190",

language = "T{\"u}rk{\c c}e",

series = "2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings",

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

pages = "1745--1748",

booktitle = "2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings",

address = "United States",

}

Gürkaynak, D & Yalçin, H 2015, RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma. in 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings., 7130190, 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1745-1748, 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015, Malatya, Turkey, 16/05/15. https://doi.org/10.1109/SIU.2015.7130190

RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma. / Gürkaynak, Deniz; Yalçin, Hülya.
2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1745-1748 7130190 (2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings).

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

TY - GEN

T1 - RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma

AU - Gürkaynak, Deniz

AU - Yalçin, Hülya

PY - 2015/6/19

Y1 - 2015/6/19

N2 - Human activity recognition has many applications in computer vision, including personal assistive robotics and smart homes/environments. Due to the large temporal and spatial variations in actions performed by humans, human action recognition has been a long-standing challenge. This paper presents a method that recognizes certain human activities based on a motion descriptor that uses 3D human skeleton data. A motion descriptor (SHOJD) is defined using the 3D distance between the most frequent key poses that occur throughout the action that is intended to be recognized. SHOJD features are then fed into an artificial neural network for classification. Experimental results indicate that the SHOJD based human action recognition system is robust with high recognition rate.

AB - Human activity recognition has many applications in computer vision, including personal assistive robotics and smart homes/environments. Due to the large temporal and spatial variations in actions performed by humans, human action recognition has been a long-standing challenge. This paper presents a method that recognizes certain human activities based on a motion descriptor that uses 3D human skeleton data. A motion descriptor (SHOJD) is defined using the 3D distance between the most frequent key poses that occur throughout the action that is intended to be recognized. SHOJD features are then fed into an artificial neural network for classification. Experimental results indicate that the SHOJD based human action recognition system is robust with high recognition rate.

KW - RGB-D imaging

KW - activity recognition

KW - motion descriptors

UR - http://www.scopus.com/inward/record.url?scp=84939166752&partnerID=8YFLogxK

U2 - 10.1109/SIU.2015.7130190

DO - 10.1109/SIU.2015.7130190

M3 - Konferans katkısı

AN - SCOPUS:84939166752

T3 - 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings

SP - 1745

EP - 1748

BT - 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015

Y2 - 16 May 2015 through 19 May 2015

ER -

Gürkaynak D, Yalçin H. RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma. In 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1745-1748. 7130190. (2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings). doi: 10.1109/SIU.2015.7130190

RGB-D Görüntülerinden Insan Aktivitesi Tanima ve Siniflandirma

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this