Publication Details

Trajectory classification based on Hidden Markov Models

MLÍCH Jozef and CHMELAŘ Petr. Trajectory classification based on Hidden Markov Models. In: Proceedings of 18th International Conference on Computer Graphics and Vision. Moscow: Lomonosov Moscow State University, 2008, pp. 101-105. ISBN 978-5-9556-0112-0.
Czech title
Klasifikace trajektorií pomocí skrytých markovových modelů
Type
conference paper
Language
english
Authors
Mlích Jozef, Ing. (DCGM FIT BUT)
Chmelař Petr, Ing. (DIFS FIT BUT)
URL
Keywords

HMM, Trajectory, Classification

Abstract

This paper presents a method for statistical modeling and classification of motion trajectories using Hidden Markov Models. Mass recordings from visual surveillance  are processed to extract objects trajectories. Hidden Markov Models of classes of behaviour are created upon some annotated trajectories. In this way, information about complex object behaviour of objects can be discovered.

Additionally, an experiment shows the successful application of Hidden Markov Models on trajectories of people in an underground station in Roma. Finally, a comparison of efficiency on different data sets, is discussed.

Published
2008
Pages
101-105
Proceedings
Proceedings of 18th International Conference on Computer Graphics and Vision
Conference
GraphiCon'2008, Moskva, RU
ISBN
978-5-9556-0112-0
Publisher
Lomonosov Moscow State University
Place
Moscow, RU
BibTeX 
@INPROCEEDINGS{FITPUB8680,
   author = "Jozef Ml\'{i}ch and Petr Chmela\v{r}",
   title = "Trajectory classification based on Hidden Markov Models",
   pages = "101--105",
   booktitle = "Proceedings of 18th International Conference on Computer Graphics and Vision",
   year = 2008,
   location = "Moscow, RU",
   publisher = "Lomonosov Moscow State University",
   ISBN = "978-5-9556-0112-0",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8680"
}
Back to top