Parallel feature tracker for extended image sequences

Richard Szeliski; Sing Bing Kang; Heung Yeung Shum

Parallel feature tracker for extended image sequences

Richard Szeliski^*, Sing Bing Kang, Heung Yeung Shum

^*Corresponding author for this work

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

10 Citations (Scopus)

Abstract

This paper presents a feature tracker for long image sequences based on simultaneously estimating the motions and deformations of a collection of adjacent image patches. By sharing common corner nodes, the patches achieve greater stability than independent patch trackers. Modeling full bilinear deformations enables tracking in sequences which have large non-translational motions and/or foreshortening effects. We demonstrate the advantages of our technique with respect to previous algorithms using experimental results.

Original language	English
Pages	241-246
Number of pages	6
Publication status	Published - 1995
Externally published	Yes
Event	International Symposium on Computer Vision, ISCV'95, Proceedings - Coral Gables, FL, USA Duration: 21 Nov 1995 → 23 Nov 1995

Conference

Conference	International Symposium on Computer Vision, ISCV'95, Proceedings
City	Coral Gables, FL, USA
Period	21/11/95 → 23/11/95

Cite this

@conference{471bf23ad08e4d64907afb23bbc6faee,

title = "Parallel feature tracker for extended image sequences",

abstract = "This paper presents a feature tracker for long image sequences based on simultaneously estimating the motions and deformations of a collection of adjacent image patches. By sharing common corner nodes, the patches achieve greater stability than independent patch trackers. Modeling full bilinear deformations enables tracking in sequences which have large non-translational motions and/or foreshortening effects. We demonstrate the advantages of our technique with respect to previous algorithms using experimental results.",

author = "Richard Szeliski and Kang, \{Sing Bing\} and Shum, \{Heung Yeung\}",

year = "1995",

language = "English",

pages = "241--246",

note = "International Symposium on Computer Vision, ISCV'95, Proceedings ; Conference date: 21-11-1995 Through 23-11-1995",

}

TY - CONF

T1 - Parallel feature tracker for extended image sequences

AU - Szeliski, Richard

AU - Kang, Sing Bing

AU - Shum, Heung Yeung

PY - 1995

Y1 - 1995

N2 - This paper presents a feature tracker for long image sequences based on simultaneously estimating the motions and deformations of a collection of adjacent image patches. By sharing common corner nodes, the patches achieve greater stability than independent patch trackers. Modeling full bilinear deformations enables tracking in sequences which have large non-translational motions and/or foreshortening effects. We demonstrate the advantages of our technique with respect to previous algorithms using experimental results.

AB - This paper presents a feature tracker for long image sequences based on simultaneously estimating the motions and deformations of a collection of adjacent image patches. By sharing common corner nodes, the patches achieve greater stability than independent patch trackers. Modeling full bilinear deformations enables tracking in sequences which have large non-translational motions and/or foreshortening effects. We demonstrate the advantages of our technique with respect to previous algorithms using experimental results.

UR - https://www.scopus.com/pages/publications/0029535744

M3 - Conference Paper

AN - SCOPUS:0029535744

SP - 241

EP - 246

T2 - International Symposium on Computer Vision, ISCV'95, Proceedings

Y2 - 21 November 1995 through 23 November 1995

ER -

Parallel feature tracker for extended image sequences

Abstract

Conference

Other files and links

Fingerprint

Cite this