Active mesh - A video representation scheme for feature seeking and tracking

Yao Wang, Ouseb Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper introduces a representation scheme for images and video sequences using nonuniform samples embedded in a mesh structure. It describes a video sequence by the nodal positions and colors in a starting frame, followed by the nodal displacements in the following frames. The nodal points are more densely distributed in regions coniaining inieresting features such as edges and corners; and are dynamically updated to follow the same fealures in successive frames. They are determined automatically by maximizing feature (e.g, gradient) magnitudes at nodal poinis, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. In order to avoid the mesh elements to become overly deformed, a penalty term is also incorporated, which measures the irregularity of the mesh structure. The noiions of shape functions and master elements commonly used in the finite element method have been employed lo simplify the numerical calculation of the energy functions and their gradients. The proposed representation is motivated by the active contour or snake model proposed by Kass, Within and Terzopoulos. The current representation retains the salient merit of the original model as a feature tracker brsed on local and collective information, while facilitating more accurate image interpolation and prediction.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Pages1558-1569
Number of pages12
Volume2094
DOIs
StatePublished - 1993
EventVisual Communications and Image Processing 1993 - Cambridge, MA, United States
Duration: Nov 7 1993Nov 7 1993

Other

OtherVisual Communications and Image Processing 1993
CountryUnited States
CityCambridge, MA
Period11/7/9311/7/93

Fingerprint

mesh
Interpolation
Mesh
interpolation
Image Interpolation
Gradient
Interpolation Error
snakes
gradients
Active Contours
shape functions
Snakes
Irregularity
Shape Function
Color
Energy Function
penalties
irregularities
Finite element method
Numerical Calculation

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Wang, Y., & Lee, O. (1993). Active mesh - A video representation scheme for feature seeking and tracking. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 2094, pp. 1558-1569) https://doi.org/10.1117/12.157916

Active mesh - A video representation scheme for feature seeking and tracking. / Wang, Yao; Lee, Ouseb.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2094 1993. p. 1558-1569.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, Y & Lee, O 1993, Active mesh - A video representation scheme for feature seeking and tracking. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 2094, pp. 1558-1569, Visual Communications and Image Processing 1993, Cambridge, MA, United States, 11/7/93. https://doi.org/10.1117/12.157916
Wang Y, Lee O. Active mesh - A video representation scheme for feature seeking and tracking. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2094. 1993. p. 1558-1569 https://doi.org/10.1117/12.157916
Wang, Yao ; Lee, Ouseb. / Active mesh - A video representation scheme for feature seeking and tracking. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2094 1993. pp. 1558-1569
@inproceedings{839fb8900b6247f49763d9888f9fe114,
title = "Active mesh - A video representation scheme for feature seeking and tracking",
abstract = "This paper introduces a representation scheme for images and video sequences using nonuniform samples embedded in a mesh structure. It describes a video sequence by the nodal positions and colors in a starting frame, followed by the nodal displacements in the following frames. The nodal points are more densely distributed in regions coniaining inieresting features such as edges and corners; and are dynamically updated to follow the same fealures in successive frames. They are determined automatically by maximizing feature (e.g, gradient) magnitudes at nodal poinis, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. In order to avoid the mesh elements to become overly deformed, a penalty term is also incorporated, which measures the irregularity of the mesh structure. The noiions of shape functions and master elements commonly used in the finite element method have been employed lo simplify the numerical calculation of the energy functions and their gradients. The proposed representation is motivated by the active contour or snake model proposed by Kass, Within and Terzopoulos. The current representation retains the salient merit of the original model as a feature tracker brsed on local and collective information, while facilitating more accurate image interpolation and prediction.",
author = "Yao Wang and Ouseb Lee",
year = "1993",
doi = "10.1117/12.157916",
language = "English (US)",
volume = "2094",
pages = "1558--1569",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Active mesh - A video representation scheme for feature seeking and tracking

AU - Wang, Yao

AU - Lee, Ouseb

PY - 1993

Y1 - 1993

N2 - This paper introduces a representation scheme for images and video sequences using nonuniform samples embedded in a mesh structure. It describes a video sequence by the nodal positions and colors in a starting frame, followed by the nodal displacements in the following frames. The nodal points are more densely distributed in regions coniaining inieresting features such as edges and corners; and are dynamically updated to follow the same fealures in successive frames. They are determined automatically by maximizing feature (e.g, gradient) magnitudes at nodal poinis, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. In order to avoid the mesh elements to become overly deformed, a penalty term is also incorporated, which measures the irregularity of the mesh structure. The noiions of shape functions and master elements commonly used in the finite element method have been employed lo simplify the numerical calculation of the energy functions and their gradients. The proposed representation is motivated by the active contour or snake model proposed by Kass, Within and Terzopoulos. The current representation retains the salient merit of the original model as a feature tracker brsed on local and collective information, while facilitating more accurate image interpolation and prediction.

AB - This paper introduces a representation scheme for images and video sequences using nonuniform samples embedded in a mesh structure. It describes a video sequence by the nodal positions and colors in a starting frame, followed by the nodal displacements in the following frames. The nodal points are more densely distributed in regions coniaining inieresting features such as edges and corners; and are dynamically updated to follow the same fealures in successive frames. They are determined automatically by maximizing feature (e.g, gradient) magnitudes at nodal poinis, while minimizing interpolation errors within individual elements, and matching errors between corresponding elements. In order to avoid the mesh elements to become overly deformed, a penalty term is also incorporated, which measures the irregularity of the mesh structure. The noiions of shape functions and master elements commonly used in the finite element method have been employed lo simplify the numerical calculation of the energy functions and their gradients. The proposed representation is motivated by the active contour or snake model proposed by Kass, Within and Terzopoulos. The current representation retains the salient merit of the original model as a feature tracker brsed on local and collective information, while facilitating more accurate image interpolation and prediction.

UR - http://www.scopus.com/inward/record.url?scp=0040525085&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0040525085&partnerID=8YFLogxK

U2 - 10.1117/12.157916

DO - 10.1117/12.157916

M3 - Conference contribution

AN - SCOPUS:0040525085

VL - 2094

SP - 1558

EP - 1569

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -