Skip to Main content Skip to Navigation
Conference papers

Detection and segmentation of moving objects in highly dynamic scenes

Aurélie Bugeau 1 Patrick Pérez 1
1 VISTA - Vision spatio-temporelle et active
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Detecting and segmenting moving objects in dynamic scenes is a hard but essential task in a number of applications such as surveillance. Most existing methods only give good results in the case of persistent or slowly changing background, or if both the objects and the background are rigid. In this paper, we propose a new method for direct detection and segmentation of foreground moving objects in the absence of such constraints. First, groups of pixels having similar motion and photometric features are extracted. For this first step only a sub-grid of image pixels is used to reduce computational cost and improve robustness to noise. We introduce the use of p-value to validate optical flow estimates and of automatic bandwidth selection in the mean shift clustering algorithm. In a second stage, segmentation of the object associated to a given cluster is performed in a MAP/MRF framework. Our method is able to handle moving camera and several different motions in the background. Experiments on challenging sequences show the performance of the proposed method and its utility for video analysis in complex scenes.
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00551596
Contributor : Aurélie Bugeau <>
Submitted on : Tuesday, January 4, 2011 - 10:38:07 AM
Last modification on : Friday, November 16, 2018 - 1:27:55 AM
Document(s) archivé(s) le : Tuesday, April 5, 2011 - 2:46:15 AM

File

CVPR.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00551596, version 1

Citation

Aurélie Bugeau, Patrick Pérez. Detection and segmentation of moving objects in highly dynamic scenes. International Conference on Computer Vision and Pattern Recognition, 2007, United States. p. ⟨hal-00551596⟩

Share

Metrics

Record views

447

Files downloads

527