Fall detection in a smart room by using a fuzzy one class support vector machine and imperfect training data

Yu, Miao and Naqvi, Syed Mohsen and Rhuma, Adel and Chambers, Jonathan (2011) Fall detection in a smart room by using a fuzzy one class support vector machine and imperfect training data. In: Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, 22 - 27 May 2011, Prague, Czech Republic.

Documents
FALL DETECTION IN A SMART ROOM BY USING A FUZZY ONE CLASS SUPPORT VECTOR MACHINE AND IMPERFECT TRAINING DATA.pdf
[img]
[Download]
[img]
Preview
PDF
FALL DETECTION IN A SMART ROOM BY USING A FUZZY ONE CLASS SUPPORT VECTOR MACHINE AND IMPERFECT TRAINING DATA.pdf - Whole Document

275kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

In this paper,we propose an efficient and robust fall detection system byusingafuzzyoneclasssupportvectormachinebasedonvideoinformation. Two cameras are used to capture the video frames from which the features are extracted. A fuzzy one class support vector machine (FOCSVM) is used to distinguish falling from other activities, such as walking, sitting, standing, bending or lying. Compared with the traditional one class support vector machine, the FOCSVM can obtain a more accurate and tight decision boundary under a training dataset with outliers. From real video sequences, the success of the method is confirmed with less non-fall samples being misclassified as falls by the classifier under an imperfect training dataset.

Keywords:voxel person, discrete Fourier transform, fuzzy one class support vector machine, fall detection, imperfect training data
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
G Mathematical and Computer Sciences > G150 Mathematical Modelling
G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:26788
Deposited On:30 Mar 2017 13:50

Repository Staff Only: item control page