Multi-Cue Learning and Visualization of Unusual Events

Rene Schuster, Samuel Schulter, Georg Poier, Martin Hirzer, Josef Birchbauer, Peter Roth, Horst Bischof, Martin Winter, Peter Schallauer

Research output: Contribution to conference(Old data) Lecture or PresentationResearchpeer-review

Abstract

Unusual event detection, i.e., identifying unspecified rare/critical events, has become one of the major challenges in visual surveillance. The main solution for this problem is to describe local or global normalness and to report events that do not fit to the estimated models. The majority of existing approaches, however, is limited to a single description (e.g., either appearance or motion) and/or builds on inflexible (unsupervised) learning techniques, both clearly degrading the practical applicability. To overcome these limitations, we demonstrate a system that is capable of extracting and modeling several representations in parallel, while in addition allows for user interaction within a continuous learning setup. Novel yet intuitive concepts of result visualization and user interaction will be presented that allow for exploiting the underlying data.
Original languageEnglish
Pages1933-1940
Publication statusPublished - 6 Nov 2011
Event11th IEEE Workshop on Visual Surveillance 2011 - Barcelona, Spain
Duration: 6 Nov 201113 Nov 2011

Conference

Conference11th IEEE Workshop on Visual Surveillance 2011
CountrySpain
CityBarcelona
Period6/11/1113/11/11

Fingerprint

Unsupervised learning
Visualization

Fields of Expertise

  • Information, Communication & Computing

Cite this

Schuster, R., Schulter, S., Poier, G., Hirzer, M., Birchbauer, J., Roth, P., ... Schallauer, P. (2011). Multi-Cue Learning and Visualization of Unusual Events. 1933-1940. 11th IEEE Workshop on Visual Surveillance 2011, Barcelona, Spain.

Multi-Cue Learning and Visualization of Unusual Events. / Schuster, Rene; Schulter, Samuel; Poier, Georg; Hirzer, Martin; Birchbauer, Josef; Roth, Peter; Bischof, Horst; Winter, Martin; Schallauer, Peter.

2011. 1933-1940 11th IEEE Workshop on Visual Surveillance 2011, Barcelona, Spain.

Research output: Contribution to conference(Old data) Lecture or PresentationResearchpeer-review

Schuster, R, Schulter, S, Poier, G, Hirzer, M, Birchbauer, J, Roth, P, Bischof, H, Winter, M & Schallauer, P 2011, 'Multi-Cue Learning and Visualization of Unusual Events' 11th IEEE Workshop on Visual Surveillance 2011, Barcelona, Spain, 6/11/11 - 13/11/11, pp. 1933-1940.
Schuster R, Schulter S, Poier G, Hirzer M, Birchbauer J, Roth P et al. Multi-Cue Learning and Visualization of Unusual Events. 2011. 11th IEEE Workshop on Visual Surveillance 2011, Barcelona, Spain.
Schuster, Rene ; Schulter, Samuel ; Poier, Georg ; Hirzer, Martin ; Birchbauer, Josef ; Roth, Peter ; Bischof, Horst ; Winter, Martin ; Schallauer, Peter. / Multi-Cue Learning and Visualization of Unusual Events. 11th IEEE Workshop on Visual Surveillance 2011, Barcelona, Spain.
@conference{4c682afb1da348568408c0a80a7cba95,
title = "Multi-Cue Learning and Visualization of Unusual Events",
abstract = "Unusual event detection, i.e., identifying unspecified rare/critical events, has become one of the major challenges in visual surveillance. The main solution for this problem is to describe local or global normalness and to report events that do not fit to the estimated models. The majority of existing approaches, however, is limited to a single description (e.g., either appearance or motion) and/or builds on inflexible (unsupervised) learning techniques, both clearly degrading the practical applicability. To overcome these limitations, we demonstrate a system that is capable of extracting and modeling several representations in parallel, while in addition allows for user interaction within a continuous learning setup. Novel yet intuitive concepts of result visualization and user interaction will be presented that allow for exploiting the underlying data.",
author = "Rene Schuster and Samuel Schulter and Georg Poier and Martin Hirzer and Josef Birchbauer and Peter Roth and Horst Bischof and Martin Winter and Peter Schallauer",
year = "2011",
month = "11",
day = "6",
language = "English",
pages = "1933--1940",
note = "11th IEEE Workshop on Visual Surveillance 2011 ; Conference date: 06-11-2011 Through 13-11-2011",

}

TY - CONF

T1 - Multi-Cue Learning and Visualization of Unusual Events

AU - Schuster, Rene

AU - Schulter, Samuel

AU - Poier, Georg

AU - Hirzer, Martin

AU - Birchbauer, Josef

AU - Roth, Peter

AU - Bischof, Horst

AU - Winter, Martin

AU - Schallauer, Peter

PY - 2011/11/6

Y1 - 2011/11/6

N2 - Unusual event detection, i.e., identifying unspecified rare/critical events, has become one of the major challenges in visual surveillance. The main solution for this problem is to describe local or global normalness and to report events that do not fit to the estimated models. The majority of existing approaches, however, is limited to a single description (e.g., either appearance or motion) and/or builds on inflexible (unsupervised) learning techniques, both clearly degrading the practical applicability. To overcome these limitations, we demonstrate a system that is capable of extracting and modeling several representations in parallel, while in addition allows for user interaction within a continuous learning setup. Novel yet intuitive concepts of result visualization and user interaction will be presented that allow for exploiting the underlying data.

AB - Unusual event detection, i.e., identifying unspecified rare/critical events, has become one of the major challenges in visual surveillance. The main solution for this problem is to describe local or global normalness and to report events that do not fit to the estimated models. The majority of existing approaches, however, is limited to a single description (e.g., either appearance or motion) and/or builds on inflexible (unsupervised) learning techniques, both clearly degrading the practical applicability. To overcome these limitations, we demonstrate a system that is capable of extracting and modeling several representations in parallel, while in addition allows for user interaction within a continuous learning setup. Novel yet intuitive concepts of result visualization and user interaction will be presented that allow for exploiting the underlying data.

M3 - (Old data) Lecture or Presentation

SP - 1933

EP - 1940

ER -