Application of SVD networks to multi-object motion-shape analysis

Sun-Yuan Kung; J. S. Taur; M. Y. Chiu

Application of SVD networks to multi-object motion-shape analysis

Sun-Yuan Kung, J. S. Taur, M. Y. Chiu

Research output: Contribution to conference › Paper › peer-review

Abstract

The paper discusses the evolution of the single object motion shape estimation (MSE) problem. Given a sequence of 2-D video images of multiple moving objects, the problem is to track the 3-D motion of the objects and reconstruct their 3-D shapes. After selection of initial feature points (FPs), the SVD may be applied to a measurement matrix formed by the FPs sequentially tracked by a video system. The distribution of singular values first reveal the information about the number of objects at hand. Then, using an algebraic-based subspace clustering method, the FPs are mapped onto their corresponding objects. Thereafter, the motion and shape are be estimated from a matrix factorization.

Original language	English (US)
Pages	413-422
Number of pages	10
State	Published - Dec 1 1994
Event	Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94) - Ermioni, GREECE Duration: Sep 6 1994 → Sep 8 1994

Other

Other	Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94)
City	Ermioni, GREECE
Period	9/6/94 → 9/8/94

All Science Journal Classification (ASJC) codes

Signal Processing
Software
Electrical and Electronic Engineering

Cite this

@conference{458319e9dc6545108cc9375abad20d86,

title = "Application of SVD networks to multi-object motion-shape analysis",

abstract = "The paper discusses the evolution of the single object motion shape estimation (MSE) problem. Given a sequence of 2-D video images of multiple moving objects, the problem is to track the 3-D motion of the objects and reconstruct their 3-D shapes. After selection of initial feature points (FPs), the SVD may be applied to a measurement matrix formed by the FPs sequentially tracked by a video system. The distribution of singular values first reveal the information about the number of objects at hand. Then, using an algebraic-based subspace clustering method, the FPs are mapped onto their corresponding objects. Thereafter, the motion and shape are be estimated from a matrix factorization.",

author = "Sun-Yuan Kung and Taur, {J. S.} and Chiu, {M. Y.}",

year = "1994",

month = dec,

day = "1",

language = "English (US)",

pages = "413--422",

note = "Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94) ; Conference date: 06-09-1994 Through 08-09-1994",

}

TY - CONF

T1 - Application of SVD networks to multi-object motion-shape analysis

AU - Kung, Sun-Yuan

AU - Taur, J. S.

AU - Chiu, M. Y.

PY - 1994/12/1

Y1 - 1994/12/1

N2 - The paper discusses the evolution of the single object motion shape estimation (MSE) problem. Given a sequence of 2-D video images of multiple moving objects, the problem is to track the 3-D motion of the objects and reconstruct their 3-D shapes. After selection of initial feature points (FPs), the SVD may be applied to a measurement matrix formed by the FPs sequentially tracked by a video system. The distribution of singular values first reveal the information about the number of objects at hand. Then, using an algebraic-based subspace clustering method, the FPs are mapped onto their corresponding objects. Thereafter, the motion and shape are be estimated from a matrix factorization.

AB - The paper discusses the evolution of the single object motion shape estimation (MSE) problem. Given a sequence of 2-D video images of multiple moving objects, the problem is to track the 3-D motion of the objects and reconstruct their 3-D shapes. After selection of initial feature points (FPs), the SVD may be applied to a measurement matrix formed by the FPs sequentially tracked by a video system. The distribution of singular values first reveal the information about the number of objects at hand. Then, using an algebraic-based subspace clustering method, the FPs are mapped onto their corresponding objects. Thereafter, the motion and shape are be estimated from a matrix factorization.

UR - http://www.scopus.com/inward/record.url?scp=0028726879&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028726879&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028726879

SP - 413

EP - 422

T2 - Proceedings of the 4th IEEE Workshop on Neural Networks for Signal Processing (NNSP'94)

Y2 - 6 September 1994 through 8 September 1994

ER -

Application of SVD networks to multi-object motion-shape analysis

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this