• Home
  1. Home
  2. Unsupervised Event Discrimination Based on Nonlinear Temporal Modelling of Activity
Scientific article
English

Unsupervised Event Discrimination Based on Nonlinear Temporal Modelling of Activity

Contributors

Bruno, Eric; Moenne-Loccoz, Nicolas; Marchand-Maillet, Stéphane

Published in

Pattern analysis and applications, vol. 7, no. 4, p. 402-410

Publication date

2004

Abstract

This paper deals with the problem of event discrimination in generic video documents. We propose an investigation on the design of an activity-based similarity measure derived from motion analysis. In an unsupervised context, our approach relies on the nonlinear temporal modeling of wavelet-based motion features directly estimated from the video frame. On the basis of the support vector machine (SVM) regression, this nonlinear model is able to learn the behavior of the motion descriptors along the temporal dimension and to capture useful information about the dynamic content of the shot. A similarity measure associated with our temporal model is then defined. This measure defines a metric between video segments according to spatial and temporal properties of the movements and provides a theoretic framework to compare, sort and classify videos. Experiments on a large annotated video database and a comparison with a similarity measure based on motion histograms shows that our approach is effective in discriminating between video events without any prior knowledge.

Keywords

  • Video analysis
  • Activity recognition
  • Motion estimation
  • SVM learning
  • Video similarity measure

UNIGE affiliation entities

UNIGE research groups

Citation (ISO format)

BRUNO, Eric, MOENNE-LOCCOZ, Nicolas, MARCHAND-MAILLET, Stéphane. Unsupervised Event Discrimination Based on Nonlinear Temporal Modelling of Activity. In: Pattern analysis and applications, 2004, vol. 7, n° 4, p. 402–410. doi: 10.1007/s10044-005-0242-9

Main files (1)

Article (Published version)

Identifiers

Additional URL for this publication

http://link.springer.com/article/10.1007/s10044-005-0242-9

Journal ISSN

1433-7541
493views
0downloads

Technical informations

Creation

06/03/2015 17:12:10

First validation

06/03/2015 17:12:10

Update

13/10/2025 21:40:41

Status update

14/03/2023 22:58:54

Last indexation

03/12/2025 07:38:20
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated