New Fast Fall Detection Method Based on Spatio-Temporal Context Tracking of Head by Using Depth Images

• Published in: Sensors (Basel, Switzerland) Vol. 15; no. 9; pp. 23004 - 23019
• Main Authors: Yang, Lei, Ren, Yanyun, Hu, Huosheng, Tian, Bo
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 11.09.2015; MDPI
• Subjects: Accidental Falls; Adult; Algorithms; Computer engineering; Dense spatio-temporal-context; depth images; fall detection; Falls; Head - physiology; Home environment; Human subjects; Humans; Image detection; Imaging, Three-Dimensional - methods; Mathematical analysis; Methods; Older people; Planes; Sensors; Single-Gauss-Model; Three dimensional; Tracking; Two dimensional; United States > US; China; depth images; Single-Gauss-Model; Dense spatio-temporal-context; fall detection

In order to deal with the problem of projection occurring in fall detection with two-dimensional (2D) grey or color images, this paper proposed a robust fall detection method based on spatio-temporal context tracking over three-dimensional (3D) depth images that are captured by the Kinect sensor. In...