Hidden Markov Models for Optical Flow Analysis in Crowds

Author

Andrade, Ernesto L. ; Blunsden, Scott ; Fisher, Robert B.

Author_Institution

Sch. of Informatics, Edinburgh Univ.

Volume

1

fYear

0

fDate

0-0 0

Firstpage

460

Lastpage

463

Abstract

This paper presents an event detector for emergencies in crowds. Assuming a single camera and a dense crowd we rely on optical flow instead of tracking statistics as a feature to extract information from the crowd video data. The optical flow features are encoded with hidden Markov models to allow for the detection of emergency or abnormal events in the crowd. In order to increase the detection sensitivity a local modelling approach is used. The results with simulated crowds show the effectiveness of the proposed approach on detecting abnormalities in dense crowds

Keywords

feature extraction; hidden Markov models; image sequences; learning (artificial intelligence); surveillance; video signal processing; abnormal event detection; crowd emergency detection; crowd video data; feature extraction; hidden Markov models; optical flow analysis; optical flow features; Event detection; Feature extraction; Gaussian processes; Hidden Markov models; Humans; Image motion analysis; Optical computing; Optical filters; Optical noise; Optical sensors;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.621

Filename

1698931