Active mesh - a feature seeking and tracking image sequence representation scheme

Yao Wang, Ouseb Lee

Research output: Contribution to journalArticle

Abstract

The paper introduces a representation scheme for image sequences using nonuniform samples embedded in a deformable mesh structure. It describes a sequence by nodal positions and colors in a starting frame, followed by nodal displacements in the following frames. The nodal points are determined automatically by maximizing feature magnitudes at nodal points, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. The motions of shape functions and master elements commonly used in the finite element method have been applied to simplify the numerical calculation of the energy functions and their gradients. The results of computer simulations proved the effectiveness of the scheme.

Original languageEnglish (US)
Pages (from-to)610-624
Number of pages15
JournalIEEE Transactions on Image Processing
Volume3
Issue number5
DOIs
StatePublished - Sep 1994

Fingerprint

Image Sequence
Mesh
Interpolation Error
Shape Function
Energy Function
Numerical Calculation
Interpolation
Simplify
Computer Simulation
Finite Element Method
Gradient
Color
Finite element method
Motion
Computer simulation

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software
  • Electrical and Electronic Engineering
  • Theoretical Computer Science

Cite this

Active mesh - a feature seeking and tracking image sequence representation scheme. / Wang, Yao; Lee, Ouseb.

In: IEEE Transactions on Image Processing, Vol. 3, No. 5, 09.1994, p. 610-624.

Research output: Contribution to journalArticle

@article{3088a86cca9344c39b86a37d5036ec4a,
title = "Active mesh - a feature seeking and tracking image sequence representation scheme",
abstract = "The paper introduces a representation scheme for image sequences using nonuniform samples embedded in a deformable mesh structure. It describes a sequence by nodal positions and colors in a starting frame, followed by nodal displacements in the following frames. The nodal points are determined automatically by maximizing feature magnitudes at nodal points, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. The motions of shape functions and master elements commonly used in the finite element method have been applied to simplify the numerical calculation of the energy functions and their gradients. The results of computer simulations proved the effectiveness of the scheme.",
author = "Yao Wang and Ouseb Lee",
year = "1994",
month = "9",
doi = "10.1109/83.334982",
language = "English (US)",
volume = "3",
pages = "610--624",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Active mesh - a feature seeking and tracking image sequence representation scheme

AU - Wang, Yao

AU - Lee, Ouseb

PY - 1994/9

Y1 - 1994/9

N2 - The paper introduces a representation scheme for image sequences using nonuniform samples embedded in a deformable mesh structure. It describes a sequence by nodal positions and colors in a starting frame, followed by nodal displacements in the following frames. The nodal points are determined automatically by maximizing feature magnitudes at nodal points, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. The motions of shape functions and master elements commonly used in the finite element method have been applied to simplify the numerical calculation of the energy functions and their gradients. The results of computer simulations proved the effectiveness of the scheme.

AB - The paper introduces a representation scheme for image sequences using nonuniform samples embedded in a deformable mesh structure. It describes a sequence by nodal positions and colors in a starting frame, followed by nodal displacements in the following frames. The nodal points are determined automatically by maximizing feature magnitudes at nodal points, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. The motions of shape functions and master elements commonly used in the finite element method have been applied to simplify the numerical calculation of the energy functions and their gradients. The results of computer simulations proved the effectiveness of the scheme.

UR - http://www.scopus.com/inward/record.url?scp=0028499962&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028499962&partnerID=8YFLogxK

U2 - 10.1109/83.334982

DO - 10.1109/83.334982

M3 - Article

VL - 3

SP - 610

EP - 624

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 5

ER -