A fast incremental approach for accurate measurement of the displacement field

Azeddine Beghdadi, Mostefa Mesbah, Jerôme Monteil

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

A fast method for accurate measurement of displacement field that combines template matching and differential techniques is proposed. This method, which is able to deal with the problems of non-rigid object movement as well as large inter frame displacements, operates in three steps. First, a sparse displacement field is obtained by a classic template matching technique. Then, this information is propagated through the overall image to obtain a dense displacement field. Finally, this field is considered as approximate solution before the use of classical differential technique for optical flow estimation. To illustrate the efficiency of the proposed procedure, a number of experimental results using both synthetic and real images are presented and discussed. The results show significant improvement over those obtained using standard multigrid approaches, especially in the cases of textured, very structured images or large inter frame displacements.

Original languageEnglish
Pages (from-to)383-399
Number of pages17
JournalImage and Vision Computing
Volume21
Issue number4
DOIs
Publication statusPublished - Apr 1 2003

Fingerprint

Template matching
Optical flows

Keywords

  • Cross-correlation
  • Motion estimation
  • Multiresolution analysis
  • Optical flow
  • Template matching

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

A fast incremental approach for accurate measurement of the displacement field. / Beghdadi, Azeddine; Mesbah, Mostefa; Monteil, Jerôme.

In: Image and Vision Computing, Vol. 21, No. 4, 01.04.2003, p. 383-399.

Research output: Contribution to journalArticle

Beghdadi, Azeddine ; Mesbah, Mostefa ; Monteil, Jerôme. / A fast incremental approach for accurate measurement of the displacement field. In: Image and Vision Computing. 2003 ; Vol. 21, No. 4. pp. 383-399.
@article{aa5f04a20aef4d9b8a44ff2e3645de62,
title = "A fast incremental approach for accurate measurement of the displacement field",
abstract = "A fast method for accurate measurement of displacement field that combines template matching and differential techniques is proposed. This method, which is able to deal with the problems of non-rigid object movement as well as large inter frame displacements, operates in three steps. First, a sparse displacement field is obtained by a classic template matching technique. Then, this information is propagated through the overall image to obtain a dense displacement field. Finally, this field is considered as approximate solution before the use of classical differential technique for optical flow estimation. To illustrate the efficiency of the proposed procedure, a number of experimental results using both synthetic and real images are presented and discussed. The results show significant improvement over those obtained using standard multigrid approaches, especially in the cases of textured, very structured images or large inter frame displacements.",
keywords = "Cross-correlation, Motion estimation, Multiresolution analysis, Optical flow, Template matching",
author = "Azeddine Beghdadi and Mostefa Mesbah and Jer{\^o}me Monteil",
year = "2003",
month = "4",
day = "1",
doi = "10.1016/S0262-8856(03)00014-3",
language = "English",
volume = "21",
pages = "383--399",
journal = "Image and Vision Computing",
issn = "0262-8856",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - A fast incremental approach for accurate measurement of the displacement field

AU - Beghdadi, Azeddine

AU - Mesbah, Mostefa

AU - Monteil, Jerôme

PY - 2003/4/1

Y1 - 2003/4/1

N2 - A fast method for accurate measurement of displacement field that combines template matching and differential techniques is proposed. This method, which is able to deal with the problems of non-rigid object movement as well as large inter frame displacements, operates in three steps. First, a sparse displacement field is obtained by a classic template matching technique. Then, this information is propagated through the overall image to obtain a dense displacement field. Finally, this field is considered as approximate solution before the use of classical differential technique for optical flow estimation. To illustrate the efficiency of the proposed procedure, a number of experimental results using both synthetic and real images are presented and discussed. The results show significant improvement over those obtained using standard multigrid approaches, especially in the cases of textured, very structured images or large inter frame displacements.

AB - A fast method for accurate measurement of displacement field that combines template matching and differential techniques is proposed. This method, which is able to deal with the problems of non-rigid object movement as well as large inter frame displacements, operates in three steps. First, a sparse displacement field is obtained by a classic template matching technique. Then, this information is propagated through the overall image to obtain a dense displacement field. Finally, this field is considered as approximate solution before the use of classical differential technique for optical flow estimation. To illustrate the efficiency of the proposed procedure, a number of experimental results using both synthetic and real images are presented and discussed. The results show significant improvement over those obtained using standard multigrid approaches, especially in the cases of textured, very structured images or large inter frame displacements.

KW - Cross-correlation

KW - Motion estimation

KW - Multiresolution analysis

KW - Optical flow

KW - Template matching

UR - http://www.scopus.com/inward/record.url?scp=0037380596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037380596&partnerID=8YFLogxK

U2 - 10.1016/S0262-8856(03)00014-3

DO - 10.1016/S0262-8856(03)00014-3

M3 - Article

VL - 21

SP - 383

EP - 399

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

IS - 4

ER -