Young children's fall prevention based on computer vision recognition

  • Authors:
  • Hana Na;Sheng Feng Qin;David Wright

  • Affiliations:
  • School of Engineering and Design, Brunel University, Uxbridge, Middlesex, United Kingdom;School of Engineering and Design, Brunel University, Uxbridge, Middlesex, United Kingdom;School of Engineering and Design, Brunel University, Uxbridge, Middlesex, United Kingdom

  • Venue:
  • ROCOM'06 Proceedings of the 6th WSEAS international conference on Robotics, control and manufacturing technology
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper a computer vision system is proposed to detect risk factors of young children's falls in the home environment and to produce actions to remove the factors. The system recognition tasks, clutter detection and children tracking, are defined in accordance with general suggestions which request a caregiver's continuous supervision to prevent young children's falls from the UK Child Accident Prevention Trust (CAPT). The current system uses only one commercial camera without any sensor or marker on the subject for practical purposes. This paper focuses on the system design and clutter detection. The algorithms for moving object and clutter detection have been developed, implemented and tested.