Background modeling and subtraction of dynamic scenes

DMCA

Background modeling and subtraction of dynamic scenes (2003)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Antoine Monnet , Anurag Mittal , Nikos Paragios , Visvanathan Ramesh

Venue:	Proc Int. Conf. Comput. Vision
Citations:	110 - 2 self

BibTeX

@INPROCEEDINGS{Monnet03backgroundmodeling,
    author = {Antoine Monnet and Anurag Mittal and Nikos Paragios and Visvanathan Ramesh},
    title = {Background modeling and subtraction of dynamic scenes},
    booktitle = {Proc Int. Conf. Comput. Vision},
    year = {2003},
    pages = {2--1305}
}

OpenURL

Abstract

Background modeling and subtraction is a core component in motion analysis. The central idea behind such module is to create a probabilistic representation of the static scene that is compared with the current input to perform subtraction. Such approach is efficient when the scene to be modeled refers to a static structure with limited perturbation. In this paper, we address the problem of modeling dynamic scenes where the assumption of a static background is not valid. Waving trees, beaches, escalators, natural scenes with rain or snow are examples. Inspired by the work proposed in [4], we propose an on-line auto-regressive model to capture and predict the behavior of such scenes. Towards detection of events we introduce a new metric that is based on a state-driven comparison between the prediction and the actual frame. Promising results demonstrate the potentials of the proposed framework. 1

Keyphrases

dynamic scene motion analysis on-line auto-regressive model core component static background limited perturbation actual frame probabilistic representation state-driven comparison central idea static structure towards detection static scene current input natural scene

DMCA