Detection of multiple moving objects using multiscale MRF with camera motion compensation

Author

Odobez, J.-M. ; Bouthemy, P.

Author_Institution

IRISA, Rennes, France

Volume

2

fYear

1994

fDate

13-16 Nov 1994

Firstpage

257

Abstract

We address the problem of detecting moving objects from a moving camera. The apparent flow field induced by the camera motion is modeled by a 2D parametric motion model and compensated for using the values of the parameters estimated by a multiresolution robust method. Motion detection is achieved through a statistical regularization approach based on multiscale Markov random field (MRF) models. Particular attention has been paid to the definition of the energy function involved and to the considered observations. This method has been validated by experiments carried out on different real image sequences

Keywords

Markov processes; cameras; image registration; image resolution; image sequences; motion compensation; motion estimation; parameter estimation; 2D parametric motion model; apparent flow field; camera motion compensation; energy function; experiments; image registration; image sequences; multiple moving objects detection; multiresolution robust method; multiscale MRF; multiscale Markov random field; observations; parameter estimation; statistical regularization; Cameras; Context modeling; Image sequences; Markov random fields; Motion compensation; Motion detection; Motion estimation; Object detection; Parameter estimation; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference

Conference_Location

Austin, TX

Print_ISBN

0-8186-6952-7

Type

conf

DOI

10.1109/ICIP.1994.413571

Filename

413571