Automatic learning of an activity-based semantic scene model

Author

Makris, Dimitrios ; Ellis, Tim

Author_Institution

Inf. Eng. Centre, City Univ., London, UK

fYear

2003

fDate

21-22 July 2003

Firstpage

183

Lastpage

188

Abstract

The paper proposes an activity-based semantic model for a scene under visual surveillance. It illustrates methods that allow unsupervised learning of the model from trajectory data derived from automatic visual surveillance cameras. Results are shown for each method. Finally, the benefits of such a model in a visual surveillance system are discussed.

Keywords

optical tracking; surveillance; target tracking; unsupervised learning; video signal processing; activity-based model; activity-based scene model; automatic learning; semantic model; semantic scene model; target tracking; trajectory data; unsupervised learning; video data; visual surveillance cameras; Cameras; Coupled mode analysis; Hidden Markov models; Inspection; Layout; Personnel; Surveillance; Target tracking; Trajectory; Unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Video and Signal Based Surveillance, 2003. Proceedings. IEEE Conference on

Print_ISBN

0-7695-1971-7

Type

conf

DOI

10.1109/AVSS.2003.1217920

Filename

1217920

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1809622