MLESAC tracking with 2D revolute-prismatic articulated models

G. McAllister; S.J. McKenna; I.W. Ricketts

doi:10.1109/ICPR.2002.1048405

MLESAC tracking with 2D revolute-prismatic articulated models

G. McAllister, S.J. McKenna, I.W. Ricketts

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

4 Citations (Scopus)

Abstract

A model for tracking articulated objects is proposed using a novel 2D revolute-prismatic joint. An extension of the RANSAC and MLESAC algorithms incorporating feature weights is used to perform robust tracking. The models are suitable for tracking certain human body structures. Limbs are modelled as constrained planar patches. A patch can rotate about a joint point that is displaced relative to the previous patch. A scenario in which the forearm is tracked is used to illustrate the method.

Original language	English
Title of host publication	Proceedings. 16th International Conference on Pattern Recognition, 2002
Editors	R. Kasturi, D. Laurendeau, C. Suen
Place of Publication	California
Publisher	IEEE Computer Society
Pages	725-728
Number of pages	4
Volume	2
ISBN (Print)	076951695X
DOIs	https://doi.org/10.1109/ICPR.2002.1048405
Publication status	Published - Aug 2002
Event	16th International Conference on Pattern Recognition - Quebec, Canada Duration: 11 Aug 2002 → 15 Aug 2002 http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8091

Conference

Conference	16th International Conference on Pattern Recognition
Country/Territory	Canada
City	Quebec
Period	11/08/02 → 15/08/02
Internet address	http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8091

Access to Document

10.1109/ICPR.2002.1048405

Cite this

@inproceedings{971bc07ab5e84f268d23c7ed2f240ce8,

title = "MLESAC tracking with 2D revolute-prismatic articulated models",

abstract = "A model for tracking articulated objects is proposed using a novel 2D revolute-prismatic joint. An extension of the RANSAC and MLESAC algorithms incorporating feature weights is used to perform robust tracking. The models are suitable for tracking certain human body structures. Limbs are modelled as constrained planar patches. A patch can rotate about a joint point that is displaced relative to the previous patch. A scenario in which the forearm is tracked is used to illustrate the method.",

author = "G. McAllister and S.J. McKenna and I.W. Ricketts",

year = "2002",

month = aug,

doi = "10.1109/ICPR.2002.1048405",

language = "English",

isbn = "076951695X ",

volume = "2",

pages = "725--728",

editor = "R. Kasturi and D. Laurendeau and C. Suen",

booktitle = "Proceedings. 16th International Conference on Pattern Recognition, 2002",

publisher = "IEEE Computer Society",

url = "http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8091",

}

McAllister, G, McKenna, SJ & Ricketts, IW 2002, MLESAC tracking with 2D revolute-prismatic articulated models. in R Kasturi, D Laurendeau & C Suen (eds), Proceedings. 16th International Conference on Pattern Recognition, 2002. vol. 2, IEEE Computer Society, California, pp. 725-728, 16th International Conference on Pattern Recognition, Quebec, Canada, 11/08/02. https://doi.org/10.1109/ICPR.2002.1048405

MLESAC tracking with 2D revolute-prismatic articulated models. / McAllister, G.; McKenna, S.J.; Ricketts, I.W.
Proceedings. 16th International Conference on Pattern Recognition, 2002. ed. / R. Kasturi; D. Laurendeau; C. Suen. Vol. 2 California: IEEE Computer Society, 2002. p. 725-728.

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

TY - GEN

T1 - MLESAC tracking with 2D revolute-prismatic articulated models

AU - McAllister, G.

AU - McKenna, S.J.

AU - Ricketts, I.W.

PY - 2002/8

Y1 - 2002/8

N2 - A model for tracking articulated objects is proposed using a novel 2D revolute-prismatic joint. An extension of the RANSAC and MLESAC algorithms incorporating feature weights is used to perform robust tracking. The models are suitable for tracking certain human body structures. Limbs are modelled as constrained planar patches. A patch can rotate about a joint point that is displaced relative to the previous patch. A scenario in which the forearm is tracked is used to illustrate the method.

AB - A model for tracking articulated objects is proposed using a novel 2D revolute-prismatic joint. An extension of the RANSAC and MLESAC algorithms incorporating feature weights is used to perform robust tracking. The models are suitable for tracking certain human body structures. Limbs are modelled as constrained planar patches. A patch can rotate about a joint point that is displaced relative to the previous patch. A scenario in which the forearm is tracked is used to illustrate the method.

UR - http://www.scopus.com/inward/record.url?scp=33751556957&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2002.1048405

DO - 10.1109/ICPR.2002.1048405

M3 - Conference contribution

AN - SCOPUS:33751556957

SN - 076951695X

VL - 2

SP - 725

EP - 728

BT - Proceedings. 16th International Conference on Pattern Recognition, 2002

A2 - Kasturi, R.

A2 - Laurendeau, D.

A2 - Suen, C.

PB - IEEE Computer Society

CY - California

T2 - 16th International Conference on Pattern Recognition

Y2 - 11 August 2002 through 15 August 2002

ER -

MLESAC tracking with 2D revolute-prismatic articulated models

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this