Fuzzy Bin-based Classification for Detecting Children’s Presence with 3D Depth Cameras

In this work, we present ChildSafe, a classification system which exploits skeletal features collected for children and adults using a 3D depth camera to classify the visual characteristics between the two age groups.  ChildSafe analyses the histograms of training samples and implements a bin-boundary-based classifyer.  We train and evaluate ChildSafe using a large dataset of visual samples collected from 150 elementary school children and 43 adults, ranging 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 a first step and an effective sub-system for designing various applications in the domain of child safety.



  • Hee Jung Yoon (heejung8@dgist.com)
  • Can Basaran (cbasaran@dgist.ac.kr)
  • Ho-Kyeong Ra (hk@dgist.ac.kr)
  • Sang Hyuk Son (son@dgist.ac.kr)
  • Taejoon Park (taejoon@hanyang.ac.kr)
  • JeongGil Ko (jeonggil.ko@etri.re.kr )


Basaran, Can, et al. “Classifying children with 3D depth cameras for enabling children’s safety applications.” Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. ACM, 2014.