PhD forum: Non supervised learning of human activities in Visual Sensor Networks

Author

Cilla, Rodrigo ; Patricio, Miguel A. ; Berlanga, Antonio ; Molina, Jose M.

Author_Institution

Comput. Sci. Dept., Univ. Carlos III de Madrid, Leganes, Spain

fYear

2009

fDate

Aug. 30 2009-Sept. 2 2009

Firstpage

1

Lastpage

2

Abstract

We outline how human activity recognition systems based on dynamic Bayesian networks using a single camera may be adapted to be used in visual sensor networks. It is assumed that current activity generates independent observations on some cameras in the network. Then, the activity is inferred by the accumulation of the evidences provided by the observations gathered. At the same time, some activities never produce observations on some cameras. Baum-Welch algorithm is modified to deal with this situation, providing some examples of when it converges.

Keywords

Bayes methods; cameras; image recognition; image sensors; unsupervised learning; Baum-Welch algorithm; camera; dynamic Bayesian networks; human activity recognition systems; nonsupervised learning; visual sensor networks; Bayesian methods; Computer science; Hidden Markov models; Humans; Labeling; Parameter estimation; Sensor systems; Smart cameras; Supervised learning; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Distributed Smart Cameras, 2009. ICDSC 2009. Third ACM/IEEE International Conference on

Conference_Location

Como

Print_ISBN

978-1-4244-4620-9

Electronic_ISBN

978-1-4244-4620-9

Type

conf

DOI

10.1109/ICDSC.2009.5289391

Filename

5289391