Multiresolution Gaussian Mixture Models for Visual Motion Estimation

R Wilson; A Calway

Multiresolution Gaussian Mixture Models for Visual Motion Estimation

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

3 Citations (Scopus)

Abstract

This paper introduces a new generalisation of scale-space and pyramids, which combines statistical modelling with a spatial representation. The representation uses the familiar concept of multiple resolutions, but applied to a Gaussian mixture representation of the image - hence the title MGMM. It is shown that MGMM can approximate any probability density and can adapt to smooth motions. After a brief presentation of the theory, it is shown how MGMM can be applied to the estimation of visual motion.

Translated title of the contribution	Multiresolution Gaussian Mixture Models for Visual Motion Estimation
Original language	English
Title of host publication	Unknown
Editors	I. Pitas
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	921 - 924
Number of pages	3
ISBN (Print)	0780367278
Publication status	Published - Oct 2001

Bibliographical note

Conference Proceedings/Title of Journal: Proceedings of the IEEE International Conference on Image Processing

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000589

Handle.net

Persistent link

Cite this

@inproceedings{df517a34c851401183176d3e3e1c0f4e,

title = "Multiresolution Gaussian Mixture Models for Visual Motion Estimation",

abstract = "This paper introduces a new generalisation of scale-space and pyramids, which combines statistical modelling with a spatial representation. The representation uses the familiar concept of multiple resolutions, but applied to a Gaussian mixture representation of the image - hence the title MGMM. It is shown that MGMM can approximate any probability density and can adapt to smooth motions. After a brief presentation of the theory, it is shown how MGMM can be applied to the estimation of visual motion.",

author = "R Wilson and A Calway",

note = "Conference Proceedings/Title of Journal: Proceedings of the IEEE International Conference on Image Processing",

year = "2001",

month = oct,

language = "English",

isbn = "0780367278",

pages = "921 -- 924",

editor = "I. Pitas",

booktitle = "Unknown",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

TY - GEN

T1 - Multiresolution Gaussian Mixture Models for Visual Motion Estimation

AU - Wilson, R

AU - Calway, A

N1 - Conference Proceedings/Title of Journal: Proceedings of the IEEE International Conference on Image Processing

PY - 2001/10

Y1 - 2001/10

N2 - This paper introduces a new generalisation of scale-space and pyramids, which combines statistical modelling with a spatial representation. The representation uses the familiar concept of multiple resolutions, but applied to a Gaussian mixture representation of the image - hence the title MGMM. It is shown that MGMM can approximate any probability density and can adapt to smooth motions. After a brief presentation of the theory, it is shown how MGMM can be applied to the estimation of visual motion.

AB - This paper introduces a new generalisation of scale-space and pyramids, which combines statistical modelling with a spatial representation. The representation uses the familiar concept of multiple resolutions, but applied to a Gaussian mixture representation of the image - hence the title MGMM. It is shown that MGMM can approximate any probability density and can adapt to smooth motions. After a brief presentation of the theory, it is shown how MGMM can be applied to the estimation of visual motion.

M3 - Conference Contribution (Conference Proceeding)

SN - 0780367278

SP - 921

EP - 924

BT - Unknown

A2 - Pitas, I.

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Multiresolution Gaussian Mixture Models for Visual Motion Estimation

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this