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

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

3 Citations (Scopus)

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 languageEnglish
Title of host publicationUbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing
PublisherAssociation for Computing Machinery, Inc
Pages343-347
Number of pages5
ISBN (Electronic)9781450329682
DOIs
Publication statusPublished - 2014 Jan 1
Event2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014 - Seattle, United States
Duration: 2014 Sep 132014 Sep 17

Publication series

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

Other

Other2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014
CountryUnited States
CitySeattle
Period14/9/1314/9/17

Fingerprint

Cameras
Bins
Classifiers

All Science Journal Classification (ASJC) codes

  • Software

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 ; Son, Sang Hyuk ; Park, Taejoon ; Ko, Jeong Gil. / 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{27cd47b436c14ef1a16dd82c482a5d2a,
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.",
author = "Can Basaran and Yoon, {Hee Jung} and Ra, {Ho Kyung} and Son, {Sang Hyuk} and Taejoon Park and Ko, {Jeong Gil}",
year = "2014",
month = "1",
day = "1",
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, 14/9/13. 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; Son, Sang Hyuk; Park, Taejoon; Ko, Jeong Gil.

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 proceedingConference contribution

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 - 2014/1/1

Y1 - 2014/1/1

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.

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

UR - http://www.scopus.com/inward/citedby.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

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). https://doi.org/10.1145/2632048.2636074