Data-driven prediction system for an environmental smartification approach to child fall accident prevention in a daily living space

Tsubasa Nose, Koji Kitainura, Mikiko Oono, Micliiko Ohkura, Yoshifunii Nishida

Research output: Contribution to journalConference articlepeer-review

Abstract

Ten thousand children are admitted to emergency rooms due to accidents every year in Tokyo. Hie most frequent accident is a fall accident. Fall accidents may occur when clnnbmg to a high place in a daily living space. Since injury prevention by human supervision does not work well, the World Health Organization recommends an environmental modification approach as an effective preventive countenneasure to this problem However, even for advanced human modeling teclinology. predicting where children can clnnb in everyday life situations reinams difficult. In the present study, the authors developed a new method for predicting places that children can clnnb in a data-driven manner by mtegratmg RGB-D cameras (Microsoft Kinect), a behavior recognition system (OpenPose). and a climbmg motion plannmg algorithm based on a rapidly exploring random tree. The present paper describes fundamental functions of the developed system and presents an evaluation of the feasibility of the prediction function.

Keywords

  • Climbing behavior
  • Configuration space
  • Data-driven simulation
  • Smart home: Injury prevention

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Data-driven prediction system for an environmental smartification approach to child fall accident prevention in a daily living space'. Together they form a unique fingerprint.

Cite this