A minimum-entropy procedure for robust motion estimation

Sylvain Boltz; Eric Wolsztynski; Eric Debreuve; Eric Thierry; Michel Barlaud; Luc Pronzato

doi:10.1109/ICIP.2006.312552

A minimum-entropy procedure for robust motion estimation

Sylvain Boltz
, Eric Wolsztynski
, Eric Debreuve
, Eric Thierry
, Michel Barlaud
, Luc Pronzato

Les Algorithmes

Research output: Chapter in Book/Report/Conference proceedings › Conference proceeding › peer-review

Abstract

We focus on motion estimation using a block matching approach and suggest using a minimum-entropy criterion. Many entropy-based estimation procedures exist, such as plug-in estimators based on Parzen windowing. We consider here an alternative that is applicable to data of any dimension and that circumvents the critical issues raised by kernel-based methods. To the best of our knowledge, this criterion has not yet been considered for image processing problems. The inherent robustness property of entropy is expected to provide a robust and efficient estimation of the motion vector of a block of a video sequence. In particular, the minimum-entropy estimator should be robust to occlusions and variations of luminance, for which standard approaches like SSD usually meet their limitations.

Original language	English
Title of host publication	2006 International Conference on Image Processing
Pages	1249-1252
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2006.312552
Publication status	Published - 2006
Externally published	Yes
Event	2006 IEEE International Conference on Image Processing, ICIP 2006 - Atlanta, GA, United States Duration: 8 Oct 2006 → 11 Oct 2006

Conference

Conference	2006 IEEE International Conference on Image Processing, ICIP 2006
Country/Territory	United States
City	Atlanta, GA
Period	8/10/06 → 11/10/06

Keywords

Adaptive estimation
Image matching
Image processing
Minimum entropy methods
Motion compensation
Robustness

Access to Document

10.1109/ICIP.2006.312552

Cite this

@inproceedings{030a973a8e6c42be89b285116e1a415d,

title = "A minimum-entropy procedure for robust motion estimation",

abstract = "We focus on motion estimation using a block matching approach and suggest using a minimum-entropy criterion. Many entropy-based estimation procedures exist, such as plug-in estimators based on Parzen windowing. We consider here an alternative that is applicable to data of any dimension and that circumvents the critical issues raised by kernel-based methods. To the best of our knowledge, this criterion has not yet been considered for image processing problems. The inherent robustness property of entropy is expected to provide a robust and efficient estimation of the motion vector of a block of a video sequence. In particular, the minimum-entropy estimator should be robust to occlusions and variations of luminance, for which standard approaches like SSD usually meet their limitations.",

keywords = "Adaptive estimation, Image matching, Image processing, Minimum entropy methods, Motion compensation, Robustness",

author = "Sylvain Boltz and Eric Wolsztynski and Eric Debreuve and Eric Thierry and Michel Barlaud and Luc Pronzato",

year = "2006",

doi = "10.1109/ICIP.2006.312552",

language = "English",

pages = "1249--1252",

booktitle = "2006 International Conference on Image Processing",

note = "2006 IEEE International Conference on Image Processing, ICIP 2006 ; Conference date: 08-10-2006 Through 11-10-2006",

}

TY - GEN

T1 - A minimum-entropy procedure for robust motion estimation

AU - Boltz, Sylvain

AU - Wolsztynski, Eric

AU - Debreuve, Eric

AU - Thierry, Eric

AU - Barlaud, Michel

AU - Pronzato, Luc

PY - 2006

Y1 - 2006

N2 - We focus on motion estimation using a block matching approach and suggest using a minimum-entropy criterion. Many entropy-based estimation procedures exist, such as plug-in estimators based on Parzen windowing. We consider here an alternative that is applicable to data of any dimension and that circumvents the critical issues raised by kernel-based methods. To the best of our knowledge, this criterion has not yet been considered for image processing problems. The inherent robustness property of entropy is expected to provide a robust and efficient estimation of the motion vector of a block of a video sequence. In particular, the minimum-entropy estimator should be robust to occlusions and variations of luminance, for which standard approaches like SSD usually meet their limitations.

AB - We focus on motion estimation using a block matching approach and suggest using a minimum-entropy criterion. Many entropy-based estimation procedures exist, such as plug-in estimators based on Parzen windowing. We consider here an alternative that is applicable to data of any dimension and that circumvents the critical issues raised by kernel-based methods. To the best of our knowledge, this criterion has not yet been considered for image processing problems. The inherent robustness property of entropy is expected to provide a robust and efficient estimation of the motion vector of a block of a video sequence. In particular, the minimum-entropy estimator should be robust to occlusions and variations of luminance, for which standard approaches like SSD usually meet their limitations.

KW - Adaptive estimation

KW - Image matching

KW - Image processing

KW - Minimum entropy methods

KW - Motion compensation

KW - Robustness

UR - https://www.scopus.com/pages/publications/70350106852

U2 - 10.1109/ICIP.2006.312552

DO - 10.1109/ICIP.2006.312552

M3 - Conference proceeding

AN - SCOPUS:70350106852

SP - 1249

EP - 1252

BT - 2006 International Conference on Image Processing

T2 - 2006 IEEE International Conference on Image Processing, ICIP 2006

Y2 - 8 October 2006 through 11 October 2006

ER -

A minimum-entropy procedure for robust motion estimation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this