A model change detection approach to dynamic scene modeling

Seon Joo Kim, Gianfranco Doretto, Jens Rittscher, Peter Tu, Nils Krahnstoever, Marc Pollefeys

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

In this work we propose a dynamic scene model to provide information about the presence of salient motion in the scene, and that could be used for focusing the attention of a pan/tilt/zoom camera, or for background modeling purposes. Rather than proposing a set of saliency detectors, we define what we mean by salient motion, and propose a precise model for it. Detecting salient motion becomes equivalent to detecting a model change. We derive optimal online procedures to solve this problem, which enable a very fast implementation. Promising results show that our model can effectively detect salient motion even in severely cluttered scenes, and while a camera is panning and tilting.

Original languageEnglish
Title of host publication6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009
Pages490-495
Number of pages6
DOIs
Publication statusPublished - 2009
Event6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009 - Genova, Italy
Duration: 2009 Sept 22009 Sept 4

Publication series

Name6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009

Other

Other6th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2009
Country/TerritoryItaly
CityGenova
Period09/9/209/9/4

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A model change detection approach to dynamic scene modeling'. Together they form a unique fingerprint.

Cite this