Silhouette Orientation Volumes for Efficient Fall Detection in Depth Videos.
IEEE J Biomed Health Inform
; 21(3): 756-763, 2017 05.
Article
em En
| MEDLINE
| ID: mdl-28113444
ABSTRACT
A novel method to detect human falls in depth videos is presented in this paper. A fast and robust shape sequence descriptor, namely the Silhouette Orientation Volume (SOV), is used to represent actions and classify falls. The SOV descriptor provides high classification accuracy even with a combination of simple associated models, such as Bag-of-Words and the Naïve Bayes classifier. Experiments on the public SDU-Fall dataset show that this new approach achieves up to 91.89% fall detection accuracy with a single-view depth camera. The classification rate is about 5% higher than the results reported in the literature. An overall accuracy of 89.63% was obtained for the six-class action recognition, which is about 25% higher than the state of the art. Moreover, a perfect silhouette-based action recognition rate of 100% is achieved on the Weizmann action dataset.
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Acidentes por Quedas
/
Processamento de Imagem Assistida por Computador
/
Reconhecimento Automatizado de Padrão
/
Monitorização Ambulatorial
Tipo de estudo:
Diagnostic_studies
/
Prognostic_studies
Limite:
Female
/
Humans
/
Male
Idioma:
En
Revista:
IEEE J Biomed Health Inform
Ano de publicação:
2017
Tipo de documento:
Article