Gaussian-like spatial priors for articulated tracking

Søren Hauberg; Stefan Horst Sommer; Kim Steenstrup Pedersen

doi:10.1007/978-3-642-15549-9_31

Gaussian-like spatial priors for articulated tracking

Søren Hauberg, Stefan Horst Sommer, Kim Steenstrup Pedersen

Department of Computer Science

23 Citations (Scopus)

Abstract

We present an analysis of the spatial covariance structure of an articulated motion prior in which joint angles have a known covariance structure. From this, a well-known, but often ignored, deficiency of the kinematic skeleton representation becomes clear: spatial variance not only depends on limb lengths, but also increases as the kinematic chains are traversed. We then present two similar Gaussian-like motion priors that are explicitly expressed spatially and as such avoids any variance coming from the representation. The resulting priors are both simple and easy to implement, yet they provide superior predictions.

Original language	English
Title of host publication	Computer Vision - ECCV 2010 : 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I
Editors	Kostas Daniilidis, Petros Maragos, Nikos Paragios
Number of pages	13
Volume	Part I
Publisher	Springer
Publication date	2010
Pages	425-437
ISBN (Print)	978-3-642-15548-2
ISBN (Electronic)	978-3-642-15549-9
DOIs	https://doi.org/10.1007/978-3-642-15549-9_31
Publication status	Published - 2010
Event	11th European Conference on Computer Vision - Heraklion, Greece Duration: 5 Sept 2010 → 11 Sept 2010 Conference number: 11

Conference

Conference	11th European Conference on Computer Vision
Number	11
Country/Territory	Greece
City	Heraklion
Period	05/09/2010 → 11/09/2010

Series	Lecture notes in computer science
Number	6311
ISSN	0302-9743

Access to Document

10.1007/978-3-642-15549-9_31

https://link.springer.com/content/pdf/10.1007/978-3-642-15549-9_31.pdf

Cite this

Hauberg, S., Sommer, S. H., & Pedersen, K. S. (2010). Gaussian-like spatial priors for articulated tracking. In K. Daniilidis, P. Maragos, & N. Paragios (Eds.), Computer Vision - ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I (Vol. Part I, pp. 425-437). Springer. https://doi.org/10.1007/978-3-642-15549-9_31

Gaussian-like spatial priors for articulated tracking. / Hauberg, Søren; Sommer, Stefan Horst ; Pedersen, Kim Steenstrup.
Computer Vision - ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I. ed. / Kostas Daniilidis; Petros Maragos; Nikos Paragios. Vol. Part I Springer, 2010. p. 425-437 (Lecture notes in computer science; No. 6311).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Hauberg, S, Sommer, SH & Pedersen, KS 2010, Gaussian-like spatial priors for articulated tracking. in K Daniilidis, P Maragos & N Paragios (eds), Computer Vision - ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I. vol. Part I, Springer, Lecture notes in computer science, no. 6311, pp. 425-437, 11th European Conference on Computer Vision, Heraklion, Greece, 05/09/2010. https://doi.org/10.1007/978-3-642-15549-9_31

Hauberg S, Sommer SH , Pedersen KS. Gaussian-like spatial priors for articulated tracking. In Daniilidis K, Maragos P, Paragios N, editors, Computer Vision - ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I. Vol. Part I. Springer. 2010. p. 425-437. (Lecture notes in computer science; No. 6311). doi: 10.1007/978-3-642-15549-9_31

Hauberg, Søren ; Sommer, Stefan Horst ; Pedersen, Kim Steenstrup. / Gaussian-like spatial priors for articulated tracking. Computer Vision - ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I. editor / Kostas Daniilidis ; Petros Maragos ; Nikos Paragios. Vol. Part I Springer, 2010. pp. 425-437 (Lecture notes in computer science; No. 6311).

@inproceedings{1f18f530936a11df928f000ea68e967b,

title = "Gaussian-like spatial priors for articulated tracking",

abstract = "We present an analysis of the spatial covariance structure of an articulated motion prior in which joint angles have a known covariance structure. From this, a well-known, but often ignored, deficiency of the kinematic skeleton representation becomes clear: spatial variance not only depends on limb lengths, but also increases as the kinematic chains are traversed. We then present two similar Gaussian-like motion priors that are explicitly expressed spatially and as such avoids any variance coming from the representation. The resulting priors are both simple and easy to implement, yet they provide superior predictions.",

author = "S{\o}ren Hauberg and Sommer, {Stefan Horst} and Pedersen, {Kim Steenstrup}",

year = "2010",

doi = "10.1007/978-3-642-15549-9_31",

language = "English",

isbn = "978-3-642-15548-2",

volume = "Part I",

series = "Lecture notes in computer science",

publisher = "Springer",

number = "6311",

pages = "425--437",

editor = "Kostas Daniilidis and Petros Maragos and Nikos Paragios",

booktitle = "Computer Vision - ECCV 2010",

note = "11th European Conference on Computer Vision, ECCV 2010 ; Conference date: 05-09-2010 Through 11-09-2010",

}

TY - GEN

T1 - Gaussian-like spatial priors for articulated tracking

AU - Hauberg, Søren

AU - Sommer, Stefan Horst

AU - Pedersen, Kim Steenstrup

N1 - Conference code: 11

PY - 2010

Y1 - 2010

N2 - We present an analysis of the spatial covariance structure of an articulated motion prior in which joint angles have a known covariance structure. From this, a well-known, but often ignored, deficiency of the kinematic skeleton representation becomes clear: spatial variance not only depends on limb lengths, but also increases as the kinematic chains are traversed. We then present two similar Gaussian-like motion priors that are explicitly expressed spatially and as such avoids any variance coming from the representation. The resulting priors are both simple and easy to implement, yet they provide superior predictions.

AB - We present an analysis of the spatial covariance structure of an articulated motion prior in which joint angles have a known covariance structure. From this, a well-known, but often ignored, deficiency of the kinematic skeleton representation becomes clear: spatial variance not only depends on limb lengths, but also increases as the kinematic chains are traversed. We then present two similar Gaussian-like motion priors that are explicitly expressed spatially and as such avoids any variance coming from the representation. The resulting priors are both simple and easy to implement, yet they provide superior predictions.

U2 - 10.1007/978-3-642-15549-9_31

DO - 10.1007/978-3-642-15549-9_31

M3 - Article in proceedings

SN - 978-3-642-15548-2

VL - Part I

T3 - Lecture notes in computer science

SP - 425

EP - 437

BT - Computer Vision - ECCV 2010

A2 - Daniilidis, Kostas

A2 - Maragos, Petros

A2 - Paragios, Nikos

PB - Springer

T2 - 11th European Conference on Computer Vision

Y2 - 5 September 2010 through 11 September 2010

ER -

Gaussian-like spatial priors for articulated tracking

Abstract

Conference

Access to Document

Fingerprint

Cite this