Publication Details

Trajectory classification using HMMs

MLÍCH Jozef, ZEMČÍK Pavel and JIŘÍK Leoš. Trajectory classification using HMMs. In: WSCG 2009 Communication Papers. Plzeň: University of West Bohemia in Pilsen, 2009, pp. 67-72. ISBN 978-80-86943-94-7.
Czech title
Trajectory classification using HMMs
Type
conference paper
Language
english
Authors
Mlích Jozef, Ing. (DCGM FIT BUT)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Jiřík Leoš, Ing. (FEEC BUT)
Keywords

Trajectory classification, Gaussian Mixture Models, Hidden Markov models, video sequences

Abstract

This paper focuses on evaluation of motion of objects through classification of their trajectories. The objects used for evaluation of the presented method are objects tracked in video sequence but the method is quite general and can be used for more general trajectories. The main potential application of the presented method is detection of abnormal behavior of humans, hand gesture detection and recognition, etc. Hidden Markov Models (HMMs) and Gaussian Mixture Models are used as the base of the the classification mechanism. The paper contains description of the method, description of experiments and their results, and conclusions.

Published
2009
Pages
67-72
Proceedings
WSCG 2009 Communication Papers
Conference
Winter School of Computer Graphics 2009, Plzeň, CZ
ISBN
978-80-86943-94-7
Publisher
University of West Bohemia in Pilsen
Place
Plzeň, CZ
BibTeX 
@INPROCEEDINGS{FITPUB8944,
   author = "Jozef Ml\'{i}ch and Pavel Zem\v{c}\'{i}k and Leo\v{s} Ji\v{r}\'{i}k",
   title = "Trajectory classification using HMMs",
   pages = "67--72",
   booktitle = "WSCG 2009 Communication Papers",
   year = 2009,
   location = "Plze\v{n}, CZ",
   publisher = "University of West Bohemia in Pilsen",
   ISBN = "978-80-86943-94-7",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8944"
}
Back to top