Classifying Children with 3D Depth Cameras for Enabling Children's Safety Applications


Basaran C., Yoon H. J. , Ra H. K. , Son S. H. , Park T., Ko J.

ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), Washington, United States Of America, 13 - 17 September 2014, pp.343-347 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1145/2632048.2636074
  • City: Washington
  • Country: United States Of America
  • Page Numbers: pp.343-347
  • Keywords: Child Classification, Kinect-based Applications

Abstract

In this work, we present ChildSafe, a classification system which exploits human skeletal features collected using 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, 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 an effective sub-system for designing various child protection applications.