Adjusting shape parameters using model-based optical flow residuals

Douglas DeCarlo; Dimitris Metaxas

doi:10.1109/TPAMI.2002.1008387

Adjusting shape parameters using model-based optical flow residuals

Douglas DeCarlo, Dimitris Metaxas

Research output: Contribution to journal › Article › peer-review

26 Scopus citations

Abstract

We present a method for estimating the shape of a deformable model using the least-squares residuals from a model-based optical flow computation. This method is built on top of an estimation framework using optical flow and image features, where optical flow affects only the motion parameters of the model. Using the results of this computation, our new method adjusts all of the parameters so that the residuals from the flow computation are minimized. We present face tracking experiments that demonstrate that this method obtains a better estimate of shape compared to related frameworks.

Original language	English (US)
Pages (from-to)	814-823
Number of pages	10
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	24
Issue number	6
DOIs	https://doi.org/10.1109/TPAMI.2002.1008387
State	Published - Jun 2002

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Keywords

Deformable models
Model-based optical flow
Nonrigid shape and motion estimation

Access to Document

10.1109/TPAMI.2002.1008387

Cite this

@article{4a51bb68fb4242bdb7a8da96ee0790a3,

title = "Adjusting shape parameters using model-based optical flow residuals",

abstract = "We present a method for estimating the shape of a deformable model using the least-squares residuals from a model-based optical flow computation. This method is built on top of an estimation framework using optical flow and image features, where optical flow affects only the motion parameters of the model. Using the results of this computation, our new method adjusts all of the parameters so that the residuals from the flow computation are minimized. We present face tracking experiments that demonstrate that this method obtains a better estimate of shape compared to related frameworks.",

keywords = "Deformable models, Model-based optical flow, Nonrigid shape and motion estimation",

author = "Douglas DeCarlo and Dimitris Metaxas",

note = "Funding Information: This research is supported by the US Army Research Office grant DAAH-04-96-1-007, the US National Science Foundation Career Award (IRI-96-24604), the US Air Force Office of Scientific Research and the US Office of Naval Research-Young Investigators Program N00014-97-1-0817, and a RuCCS postdoctoral fellowship.",

year = "2002",

month = jun,

doi = "10.1109/TPAMI.2002.1008387",

language = "English (US)",

volume = "24",

pages = "814--823",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "6",

}

TY - JOUR

T1 - Adjusting shape parameters using model-based optical flow residuals

AU - DeCarlo, Douglas

AU - Metaxas, Dimitris

N1 - Funding Information: This research is supported by the US Army Research Office grant DAAH-04-96-1-007, the US National Science Foundation Career Award (IRI-96-24604), the US Air Force Office of Scientific Research and the US Office of Naval Research-Young Investigators Program N00014-97-1-0817, and a RuCCS postdoctoral fellowship.

PY - 2002/6

Y1 - 2002/6

N2 - We present a method for estimating the shape of a deformable model using the least-squares residuals from a model-based optical flow computation. This method is built on top of an estimation framework using optical flow and image features, where optical flow affects only the motion parameters of the model. Using the results of this computation, our new method adjusts all of the parameters so that the residuals from the flow computation are minimized. We present face tracking experiments that demonstrate that this method obtains a better estimate of shape compared to related frameworks.

AB - We present a method for estimating the shape of a deformable model using the least-squares residuals from a model-based optical flow computation. This method is built on top of an estimation framework using optical flow and image features, where optical flow affects only the motion parameters of the model. Using the results of this computation, our new method adjusts all of the parameters so that the residuals from the flow computation are minimized. We present face tracking experiments that demonstrate that this method obtains a better estimate of shape compared to related frameworks.

KW - Deformable models

KW - Model-based optical flow

KW - Nonrigid shape and motion estimation

UR - http://www.scopus.com/inward/record.url?scp=0036602955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036602955&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2002.1008387

DO - 10.1109/TPAMI.2002.1008387

M3 - Article

AN - SCOPUS:0036602955

SN - 0162-8828

VL - 24

SP - 814

EP - 823

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 6

ER -

Adjusting shape parameters using model-based optical flow residuals

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this