Fall Detection in RGB-D Videos for Elderly Care
Paper i proceeding, 2015

This paper addresses issues in fall detection from videos. Since it has been a broadly accepted intuition that a falling person usually undergoes large physical movement and displacement in a short time interval, the study is thus focused on measuring the intensity and temporal variation of pose change and body motion. The main novelties of this paper include: (a) characterizing pose/motion dynamics based on centroid velocity, head-to-centroid distance, histogram of oriented gradients and optical flow; (b) extracting compact features based on the mean and variance of pose/motion dynamics; (c) detecting human by combining depth information and background mixture models. Experiments have been conducted on an RGB-D video dataset for fall detection. Tests and evaluations show the effectiveness of the proposed method.

appearance

Fall detection

elderly care

RGB-D video

healthcare

Shape

optical flow

Författare

Yixiao Yun

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik

Christopher Innocenti

Chalmers, Signaler och system

Gustav Nero

Chalmers, Signaler och system

Henrik Lindén

Chalmers, Signaler och system

Irene Yu-Hua Gu

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik

17th IEEE Int'l conf. on E-Health, Networking, Application & Services (HealthCom'15), 2015

6-
978-1-4673-8325-7 (ISBN)

Styrkeområden

Informations- och kommunikationsteknik

Livsvetenskaper och teknik (2010-2018)

Ämneskategorier

Signalbehandling

Datorseende och robotik (autonoma system)

Medicinsk bildbehandling

DOI

10.1109/HealthCom.2015.7454537

ISBN

978-1-4673-8325-7

Mer information

Senast uppdaterat

2022-03-02