Journal of Real-Time Image Processing

, Volume 9, Issue 4, pp 635–646

Fall detection system using Kinect’s infrared sensor

Original Research Paper

DOI: 10.1007/s11554-012-0246-9

Cite this article as:
Mastorakis, G. & Makris, D. J Real-Time Image Proc (2014) 9: 635. doi:10.1007/s11554-012-0246-9

Abstract

This paper presents a novel fall detection system based on the Kinect sensor. The system runs in real-time and is capable of detecting walking falls accurately and robustly without taking into account any false positive activities (i.e. lying on the floor). Velocity and inactivity calculations are performed to decide whether a fall has occurred. The key novelty of our approach is measuring the velocity based on the contraction or expansion of the width, height and depth of the 3D bounding box. By explicitly using the 3D bounding box, our algorithm requires no pre-knowledge of the scene (i.e. floor), as the set of detected actions are adequate to complete the process of fall detection.

Keywords

Kinect Fall detection Home assistance Real-time processing 3D bounding box analysis 

Supplementary material

View video

AVI (465 KB)

View video

AVI (995 KB)

View video

AVI (671 KB)

View video

AVI (1591 KB)

View video

AVI (411 KB)

View video

AVI (559 KB)

View video

AVI (420 KB)

View video

AVI (1941 KB)

View video

AVI (773 KB)

View video

AVI (786 KB)

View video

AVI (491 KB)

View video

AVI (563 KB)

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  1. 1.Faculty of Computing, Information Systems and Mathematics, Digital Imaging Research CentreKingston UniversitySurreyUK