Background Modeling and Subtraction of Dynamic Scenes

  • Authors:
  • Antoine Monnet;Anurag Mittal;Nikos Paragios;Visvanathan Ramesh

  • Affiliations:
  • -;-;-;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Background modeling and subtraction is a core componentin motion analysis. The central idea behind such moduleis to create a probabilistic representation of the staticscene that is compared with the current input to performsubtraction. Such approach is efficient when the scene to bemodeled refers to a static structure with limited perturbation.In this paper, we address the problem of modeling dynamicscenes where the assumption of a static backgroundis not valid. Waving trees, beaches, escalators, naturalscenes with rain or snow are examples. Inspired by the workproposed in [4], we propose an on-line auto-regressivemodel to capture and predict the behavior of such scenes.Towards detection of events we introduce a new metric thatis based on a state-driven comparison between the predictionand the actual frame. Promising results demonstratethe potentials of the proposed framework.