Posture recognition based fall detection system for monitoring an elderly person in a smart home environment

Yu, Miao and Rhuma, Adel and Naqvi, Syed Mohsen and Wang, Liang and Chambers, Jonathan (2012) Posture recognition based fall detection system for monitoring an elderly person in a smart home environment. IEEE Transactions on Information Technology in Biomedicine, 16 (6). pp. 1274-1286. ISSN 1089-7771

Documents
Posture Recognition Based Fall Detection System For Monitoring An Elderly Person In A Smart Home Environment.pdf
[img]
[Download]
[img]
Preview
PDF
Posture Recognition Based Fall Detection System For Monitoring An Elderly Person In A Smart Home Environment.pdf - Whole Document

6MB
Item Type:Article
Item Status:Live Archive

Abstract

We propose a novel computer vision based fall detection system for monitoring an elderly person in a home care application. Background subtraction is applied to extract the foreground human body and the result is improved by using certain post-processing. Information from ellipse fitting and a projection histogram along the axes of the ellipse are used as the features for distinguishing different postures of the human. These features are then fed into a directed acyclic graph support vector machine (DAGSVM) for posture classification, the result of which is then combined with derived floor information to detect a fall. From a dataset of 15 people, we show that our fall detection system can achieve a high fall detection rate (97.08%) and a very low false detection rate (0.8%) in a simulated home environment.

Keywords:Health care, assistive living, fall detection, multi-class classi?cation, DAGSVM, system integration
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
G Mathematical and Computer Sciences > G760 Machine Learning
G Mathematical and Computer Sciences > G740 Computer Vision
G Mathematical and Computer Sciences > G120 Applied Mathematics
Divisions:College of Science > School of Computer Science
ID Code:26775
Deposited On:29 Mar 2017 10:03

Repository Staff Only: item control page