Classifying children with 3D depth cameras for enabling children's safety applications

Can Basaran; Hee Jung Yoon; Ho Kyung Ra; Sang Hyuk Son; Taejoon Park; Jeong Gil Ko

doi:10.1145/2632048.2636074

Classifying children with 3D depth cameras for enabling children's safety applications

Can Basaran, Hee Jung Yoon, Ho Kyung Ra, Sang Hyuk Son, Taejoon Park, Jeong Gil Ko

Department of Electrical Engineering and Computer Science

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

9 Scopus citations

Abstract

In this work, we present ChildSafe, a classification sys- Tem which exploits human skeletal features collected us- ing a 3D depth camera to classify visual characteristics between children and adults. ChildSafe analyzes the histograms of training samples and implements a bin- boundary-based classifier. We train and evaluate Child- Safe using a large dataset of visual samples collected from 150 elementary school children and 43 adults, rang- ing in the ages of 7 and 50. Our results suggest that ChildSafe successfully detects children with a proper classification rate of up to 97%, a false negative rate of as low as 1.82%, and a low false positive rate of 1.46%. We envision this work as an effective sub-system for de- signing various child protection applications.

Original language	English
Title of host publication	UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Publisher	Association for Computing Machinery, Inc
Pages	343-347
Number of pages	5
ISBN (Electronic)	9781450329682
DOIs	https://doi.org/10.1145/2632048.2636074
State	Published - 2014
Event	2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014 - Seattle, United States Duration: 13 Sep 2014 → 17 Sep 2014

Publication series

Name	UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing

Conference

Conference	2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014
Country/Territory	United States
City	Seattle
Period	13/09/14 → 17/09/14

Bibliographical note

Publisher Copyright:
Copyright © 2014 by the Association for Computing Machinery, Inc. (ACM).

Keywords

Child classification
Kinect-based applications

Access to Document

10.1145/2632048.2636074

Cite this

Basaran, C., Yoon, H. J., Ra, H. K., Son, S. H., Park, T., & Ko, J. G. (2014). Classifying children with 3D depth cameras for enabling children's safety applications. In UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 343-347). (UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing). Association for Computing Machinery, Inc. https://doi.org/10.1145/2632048.2636074

Basaran, Can ; Yoon, Hee Jung ; Ra, Ho Kyung et al. / Classifying children with 3D depth cameras for enabling children's safety applications. UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, 2014. pp. 343-347 (UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing).

@inproceedings{c5e50adebd354531a5aaffcf1a49b863,

title = "Classifying children with 3D depth cameras for enabling children's safety applications",

abstract = "In this work, we present ChildSafe, a classification sys- Tem which exploits human skeletal features collected us- ing a 3D depth camera to classify visual characteristics between children and adults. ChildSafe analyzes the histograms of training samples and implements a bin- boundary-based classifier. We train and evaluate Child- Safe using a large dataset of visual samples collected from 150 elementary school children and 43 adults, rang- ing in the ages of 7 and 50. Our results suggest that ChildSafe successfully detects children with a proper classification rate of up to 97%, a false negative rate of as low as 1.82%, and a low false positive rate of 1.46%. We envision this work as an effective sub-system for de- signing various child protection applications.",

keywords = "Child classification, Kinect-based applications",

author = "Can Basaran and Yoon, {Hee Jung} and Ra, {Ho Kyung} and Son, {Sang Hyuk} and Taejoon Park and Ko, {Jeong Gil}",

note = "Publisher Copyright: Copyright {\textcopyright} 2014 by the Association for Computing Machinery, Inc. (ACM).; 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014 ; Conference date: 13-09-2014 Through 17-09-2014",

year = "2014",

doi = "10.1145/2632048.2636074",

language = "English",

series = "UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing",

publisher = "Association for Computing Machinery, Inc",

pages = "343--347",

booktitle = "UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing",

}

Basaran, C, Yoon, HJ, Ra, HK, Son, SH, Park, T & Ko, JG 2014, Classifying children with 3D depth cameras for enabling children's safety applications. in UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Association for Computing Machinery, Inc, pp. 343-347, 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014, Seattle, United States, 13/09/14. https://doi.org/10.1145/2632048.2636074

Classifying children with 3D depth cameras for enabling children's safety applications. / Basaran, Can; Yoon, Hee Jung; Ra, Ho Kyung et al.
UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, 2014. p. 343-347 (UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing).

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

TY - GEN

T1 - Classifying children with 3D depth cameras for enabling children's safety applications

AU - Basaran, Can

AU - Yoon, Hee Jung

AU - Ra, Ho Kyung

AU - Son, Sang Hyuk

AU - Park, Taejoon

AU - Ko, Jeong Gil

PY - 2014

Y1 - 2014

N2 - In this work, we present ChildSafe, a classification sys- Tem which exploits human skeletal features collected us- ing a 3D depth camera to classify visual characteristics between children and adults. ChildSafe analyzes the histograms of training samples and implements a bin- boundary-based classifier. We train and evaluate Child- Safe using a large dataset of visual samples collected from 150 elementary school children and 43 adults, rang- ing in the ages of 7 and 50. Our results suggest that ChildSafe successfully detects children with a proper classification rate of up to 97%, a false negative rate of as low as 1.82%, and a low false positive rate of 1.46%. We envision this work as an effective sub-system for de- signing various child protection applications.

AB - In this work, we present ChildSafe, a classification sys- Tem which exploits human skeletal features collected us- ing a 3D depth camera to classify visual characteristics between children and adults. ChildSafe analyzes the histograms of training samples and implements a bin- boundary-based classifier. We train and evaluate Child- Safe using a large dataset of visual samples collected from 150 elementary school children and 43 adults, rang- ing in the ages of 7 and 50. Our results suggest that ChildSafe successfully detects children with a proper classification rate of up to 97%, a false negative rate of as low as 1.82%, and a low false positive rate of 1.46%. We envision this work as an effective sub-system for de- signing various child protection applications.

KW - Child classification

KW - Kinect-based applications

UR - http://www.scopus.com/inward/record.url?scp=84908593692&partnerID=8YFLogxK

U2 - 10.1145/2632048.2636074

DO - 10.1145/2632048.2636074

M3 - Conference contribution

AN - SCOPUS:84908593692

T3 - UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing

SP - 343

EP - 347

BT - UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing

PB - Association for Computing Machinery, Inc

T2 - 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014

Y2 - 13 September 2014 through 17 September 2014

ER -

Basaran C, Yoon HJ, Ra HK, Son SH, Park T, Ko JG. Classifying children with 3D depth cameras for enabling children's safety applications. In UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc. 2014. p. 343-347. (UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing). doi: 10.1145/2632048.2636074

Classifying children with 3D depth cameras for enabling children's safety applications

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this