Linear Prediction Based Mixture Models for Event Detection in Video Sequences

Dierck Matern; Alexandru Paul Condurache; Alfred Mertins

doi:10.1007/978-3-642-21257-4_4

Linear Prediction Based Mixture Models for Event Detection in Video Sequences

Dierck Matern, Alexandru Paul Condurache, Alfred Mertins

Institute of Signal Processing

Abstract

In this paper, we propose a method for the detection of irregularities in time series, based on linear prediction. We demonstrate how we can estimate the linear predictor by solving the Yule Walker equations, and how we can combine several predictors in a simple mixture model. In several tests, we compare our model to a Gaussian mixture and a hidden Markov model approach. We successfully apply our method to event detection in a video sequence.

Original language	English
Title of host publication	Pattern Recognition and Image Analysis
Editors	Jordi Vitrià, João Miguel Sanches, Mario Hernández
Number of pages	8
Volume	6669
Place of Publication	Berlin, Heidelberg
Publisher	Springer Berlin Heidelberg
Publication date	01.06.2011
Pages	25-32
ISBN (Print)	978-3-642-21256-7
ISBN (Electronic)	978-3-642-21257-4
DOIs	https://doi.org/10.1007/978-3-642-21257-4_4
Publication status	Published - 01.06.2011
Event	5th Iberian Conference on Pattern Recognition and Image Analysis - Las Palmas de Gran Canaria, Spain Duration: 08.06.2011 → 10.06.2011 Conference number: 85429

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-642-21257-4_4

Cite this

Matern, D., Condurache, A. P., & Mertins, A. (2011). Linear Prediction Based Mixture Models for Event Detection in Video Sequences. In J. Vitrià, J. M. Sanches, & M. Hernández (Eds.), Pattern Recognition and Image Analysis (Vol. 6669, pp. 25-32). (Lecture Notes in Computer Science ; Vol. 6669 LNCS). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-21257-4_4

@inproceedings{4ec1233ba42d44048d5df7e5b46cc783,

title = "Linear Prediction Based Mixture Models for Event Detection in Video Sequences",

abstract = "In this paper, we propose a method for the detection of irregularities in time series, based on linear prediction. We demonstrate how we can estimate the linear predictor by solving the Yule Walker equations, and how we can combine several predictors in a simple mixture model. In several tests, we compare our model to a Gaussian mixture and a hidden Markov model approach. We successfully apply our method to event detection in a video sequence.",

author = "Dierck Matern and Condurache, {Alexandru Paul} and Alfred Mertins",

year = "2011",

month = jun,

day = "1",

doi = "10.1007/978-3-642-21257-4_4",

language = "English",

isbn = "978-3-642-21256-7",

volume = "6669",

series = "Lecture Notes in Computer Science ",

publisher = "Springer Berlin Heidelberg",

pages = "25--32",

editor = "Jordi Vitri{\`a} and Sanches, {Jo{\~a}o Miguel} and Mario Hern{\'a}ndez",

booktitle = "Pattern Recognition and Image Analysis",

note = "5th Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2011 ; Conference date: 08-06-2011 Through 10-06-2011",

}

Matern, D, Condurache, AP & Mertins, A 2011, Linear Prediction Based Mixture Models for Event Detection in Video Sequences. in J Vitrià, JM Sanches & M Hernández (eds), Pattern Recognition and Image Analysis. vol. 6669, Lecture Notes in Computer Science , vol. 6669 LNCS, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 25-32, 5th Iberian Conference on Pattern Recognition and Image Analysis, Las Palmas de Gran Canaria, Spain, 08.06.11. https://doi.org/10.1007/978-3-642-21257-4_4

Linear Prediction Based Mixture Models for Event Detection in Video Sequences. / Matern, Dierck; Condurache, Alexandru Paul; Mertins, Alfred.
Pattern Recognition and Image Analysis. ed. / Jordi Vitrià; João Miguel Sanches; Mario Hernández. Vol. 6669 Berlin, Heidelberg: Springer Berlin Heidelberg, 2011. p. 25-32 (Lecture Notes in Computer Science ; Vol. 6669 LNCS).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Linear Prediction Based Mixture Models for Event Detection in Video Sequences

AU - Matern, Dierck

AU - Condurache, Alexandru Paul

AU - Mertins, Alfred

N1 - Conference code: 85429

PY - 2011/6/1

Y1 - 2011/6/1

N2 - In this paper, we propose a method for the detection of irregularities in time series, based on linear prediction. We demonstrate how we can estimate the linear predictor by solving the Yule Walker equations, and how we can combine several predictors in a simple mixture model. In several tests, we compare our model to a Gaussian mixture and a hidden Markov model approach. We successfully apply our method to event detection in a video sequence.

AB - In this paper, we propose a method for the detection of irregularities in time series, based on linear prediction. We demonstrate how we can estimate the linear predictor by solving the Yule Walker equations, and how we can combine several predictors in a simple mixture model. In several tests, we compare our model to a Gaussian mixture and a hidden Markov model approach. We successfully apply our method to event detection in a video sequence.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-79960007427&origin=inward&txGid=c65115cce9641dfffc368ea8bc77aeb0

U2 - 10.1007/978-3-642-21257-4_4

DO - 10.1007/978-3-642-21257-4_4

M3 - Conference contribution

SN - 978-3-642-21256-7

VL - 6669

T3 - Lecture Notes in Computer Science

SP - 25

EP - 32

BT - Pattern Recognition and Image Analysis

A2 - Vitrià, Jordi

A2 - Sanches, João Miguel

A2 - Hernández, Mario

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - 5th Iberian Conference on Pattern Recognition and Image Analysis

Y2 - 8 June 2011 through 10 June 2011

ER -

Linear Prediction Based Mixture Models for Event Detection in Video Sequences

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this