Region segmentation based on active mesh representation of motion: comparison of parallel and sequential approaches

Yao Wang; Xia Ming Hsieh; Jian Hong Hu; Ouseb Lee

Region segmentation based on active mesh representation of motion: comparison of parallel and sequential approaches

Yao Wang, Xia Ming Hsieh, Jian Hong Hu, Ouseb Lee

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

An active mesh representation of motion has been developed by the authors. It describes the motion in an image sequence by the trajectories of a set of nodes that form a mesh (also known as a control grid). In this paper we investigate how to cluster the nodes, or equivalently the mesh elements, so that the nodes in the same group have similar global motions. We present and compare two approaches. The parallel approach first finds a set of global motion parameters for each element and then partition these parameters using the K-means clustering algorithm; The sequential (or layered) approach recursively extracts the nodes with the dominant motion from all the nodes, using a modified robust regression algorithm.

Original language	English (US)
Title of host publication	IEEE International Conference on Image Processing
Editors	Anon
Publisher	IEEE
Pages	185-188
Number of pages	4
Volume	2
State	Published - 1996
Event	Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3) - Washington, DC, USA Duration: Oct 23 1995 → Oct 26 1995

Other

Other	Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3)
City	Washington, DC, USA
Period	10/23/95 → 10/26/95

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Hardware and Architecture
Electrical and Electronic Engineering

Cite this

Wang, Y, Hsieh, XM, Hu, JH & Lee, O 1996, Region segmentation based on active mesh representation of motion: comparison of parallel and sequential approaches. in Anon (ed.), IEEE International Conference on Image Processing. vol. 2, IEEE, pp. 185-188, Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3), Washington, DC, USA, 10/23/95.

@inproceedings{cda08ce2dad245c3a38e8c35a403e39e,

title = "Region segmentation based on active mesh representation of motion: comparison of parallel and sequential approaches",

abstract = "An active mesh representation of motion has been developed by the authors. It describes the motion in an image sequence by the trajectories of a set of nodes that form a mesh (also known as a control grid). In this paper we investigate how to cluster the nodes, or equivalently the mesh elements, so that the nodes in the same group have similar global motions. We present and compare two approaches. The parallel approach first finds a set of global motion parameters for each element and then partition these parameters using the K-means clustering algorithm; The sequential (or layered) approach recursively extracts the nodes with the dominant motion from all the nodes, using a modified robust regression algorithm.",

author = "Yao Wang and Hsieh, {Xia Ming} and Hu, {Jian Hong} and Ouseb Lee",

year = "1996",

language = "English (US)",

volume = "2",

pages = "185--188",

editor = "Anon",

booktitle = "IEEE International Conference on Image Processing",

publisher = "IEEE",

note = "Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3) ; Conference date: 23-10-1995 Through 26-10-1995",

}

TY - GEN

T1 - Region segmentation based on active mesh representation of motion

T2 - Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3)

AU - Wang, Yao

AU - Hsieh, Xia Ming

AU - Hu, Jian Hong

AU - Lee, Ouseb

PY - 1996

Y1 - 1996

N2 - An active mesh representation of motion has been developed by the authors. It describes the motion in an image sequence by the trajectories of a set of nodes that form a mesh (also known as a control grid). In this paper we investigate how to cluster the nodes, or equivalently the mesh elements, so that the nodes in the same group have similar global motions. We present and compare two approaches. The parallel approach first finds a set of global motion parameters for each element and then partition these parameters using the K-means clustering algorithm; The sequential (or layered) approach recursively extracts the nodes with the dominant motion from all the nodes, using a modified robust regression algorithm.

AB - An active mesh representation of motion has been developed by the authors. It describes the motion in an image sequence by the trajectories of a set of nodes that form a mesh (also known as a control grid). In this paper we investigate how to cluster the nodes, or equivalently the mesh elements, so that the nodes in the same group have similar global motions. We present and compare two approaches. The parallel approach first finds a set of global motion parameters for each element and then partition these parameters using the K-means clustering algorithm; The sequential (or layered) approach recursively extracts the nodes with the dominant motion from all the nodes, using a modified robust regression algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0029753610&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029753610&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029753610

VL - 2

SP - 185

EP - 188

BT - IEEE International Conference on Image Processing

A2 - Anon, null

PB - IEEE

Y2 - 23 October 1995 through 26 October 1995

ER -

Region segmentation based on active mesh representation of motion: comparison of parallel and sequential approaches

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this