View-based adaptive affine tracking

Fernando de la Torre; Shaogang Gong; Stephen McKenna

doi:10.1007/BFb0055707

View-based adaptive affine tracking

Fernando de la Torre (Lead / Corresponding author), Shaogang Gong (Lead / Corresponding author), Stephen McKenna (Lead / Corresponding author)

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

18 Citations (Scopus)

Abstract

We propose a model for view-based adaptive affine tracking of moving objects. We avoid the need for feature-based matching in establishing correspondences through learning landmarks. We use an effective bootstrapping process based on colour segmentation and selective attention. We recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate our approach.

Original language	English
Title of host publication	Computer Vision — ECCV'98
Subtitle of host publication	5th European Conference on Computer Vision Freiburg, Germany, June, 2–6, 1998 Proceedings
Editors	Hans Burkhardt, Bernd Neumann
Place of Publication	Berlin
Publisher	Springer
Pages	828-842
Number of pages	15
Volume	1
ISBN (Electronic)	9783540693543
ISBN (Print)	9783540645696
DOIs	https://doi.org/10.1007/BFb0055707
Publication status	Published - 1998
Event	5th European Conference on Computer Vision - Freiburg, Germany Duration: 2 Jun 1998 → 6 Jun 1998

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	1406
ISSN (Print)	0302-9743

Conference

Conference	5th European Conference on Computer Vision
Abbreviated title	ECCV'98
Country/Territory	Germany
City	Freiburg
Period	2/06/98 → 6/06/98

Access to Document

10.1007/BFb0055707

Cite this

@inproceedings{e4cf3320b1b949f2a4ae2cdc0d400214,

title = "View-based adaptive affine tracking",

abstract = "We propose a model for view-based adaptive affine tracking of moving objects. We avoid the need for feature-based matching in establishing correspondences through learning landmarks. We use an effective bootstrapping process based on colour segmentation and selective attention. We recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate our approach.",

author = "{de la Torre}, Fernando and Shaogang Gong and Stephen McKenna",

year = "1998",

doi = "10.1007/BFb0055707",

language = "English",

isbn = "9783540645696",

volume = "1",

series = "Lecture notes in computer science",

publisher = "Springer ",

pages = "828--842",

editor = "Burkhardt, {Hans } and Neumann, {Bernd }",

booktitle = "Computer Vision — ECCV'98",

note = "5th European Conference on Computer Vision , ECCV'98 ; Conference date: 02-06-1998 Through 06-06-1998",

}

de la Torre, F, Gong, S & McKenna, S 1998, View-based adaptive affine tracking. in H Burkhardt & B Neumann (eds), Computer Vision — ECCV'98: 5th European Conference on Computer Vision Freiburg, Germany, June, 2–6, 1998 Proceedings. vol. 1, Lecture notes in computer science, vol. 1406, Springer , Berlin, pp. 828-842, 5th European Conference on Computer Vision , Freiburg, Germany, 2/06/98. https://doi.org/10.1007/BFb0055707

View-based adaptive affine tracking. / de la Torre, Fernando (Lead / Corresponding author); Gong, Shaogang (Lead / Corresponding author); McKenna, Stephen (Lead / Corresponding author).
Computer Vision — ECCV'98: 5th European Conference on Computer Vision Freiburg, Germany, June, 2–6, 1998 Proceedings. ed. / Hans Burkhardt; Bernd Neumann. Vol. 1 Berlin: Springer , 1998. p. 828-842 (Lecture notes in computer science; Vol. 1406).

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

TY - GEN

T1 - View-based adaptive affine tracking

AU - de la Torre, Fernando

AU - Gong, Shaogang

AU - McKenna, Stephen

PY - 1998

Y1 - 1998

N2 - We propose a model for view-based adaptive affine tracking of moving objects. We avoid the need for feature-based matching in establishing correspondences through learning landmarks. We use an effective bootstrapping process based on colour segmentation and selective attention. We recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate our approach.

AB - We propose a model for view-based adaptive affine tracking of moving objects. We avoid the need for feature-based matching in establishing correspondences through learning landmarks. We use an effective bootstrapping process based on colour segmentation and selective attention. We recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate our approach.

U2 - 10.1007/BFb0055707

DO - 10.1007/BFb0055707

M3 - Conference contribution

SN - 9783540645696

VL - 1

T3 - Lecture notes in computer science

SP - 828

EP - 842

BT - Computer Vision — ECCV'98

A2 - Burkhardt, Hans

A2 - Neumann, Bernd

PB - Springer

CY - Berlin

T2 - 5th European Conference on Computer Vision

Y2 - 2 June 1998 through 6 June 1998

ER -

View-based adaptive affine tracking

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this