Bayesian body localization using mixture of nonlinear shape models

Jiayong Zhang, Robert Collins, Yanxi Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

We present a 2D model-based approach to localizing human body in images viewed from arbitrary and unknown angles. The central component is a statistical shape representation of the nonrigid and articulated body contours, where a nonlinear deformation is decomposed based on the concept of parts. Several image cues are combined to relate the body configuration to the observed image, with self-occlusion explicitly treated. To accommodate large viewpoint changes, a mixture of view-dependent models is employed. Inference is done by direct sampling of the posterior mixture, using Sequential Monte Carlo (SMC) simulation enhanced with annealing and kernel move. The fitting method is independent of the number of mixture components, and does not require the preselection of a "correct" viewpoint. The models were trained on a large number of interactively labeled gait images. Preliminary tests demonstrated the feasibility of the proposed approach.

Original languageEnglish (US)
Title of host publicationProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pages725-732
Number of pages8
DOIs
StatePublished - Dec 1 2005
EventProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China
Duration: Oct 17 2005Oct 20 2005

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
VolumeI

Other

OtherProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
CountryChina
CityBeijing
Period10/17/0510/20/05

Fingerprint

Annealing
Sampling
Monte Carlo simulation

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Zhang, J., Collins, R., & Liu, Y. (2005). Bayesian body localization using mixture of nonlinear shape models. In Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 (pp. 725-732). [1541325] (Proceedings of the IEEE International Conference on Computer Vision; Vol. I). https://doi.org/10.1109/ICCV.2005.45
Zhang, Jiayong ; Collins, Robert ; Liu, Yanxi. / Bayesian body localization using mixture of nonlinear shape models. Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. 2005. pp. 725-732 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{7d126ee94de54e579a66357393a5eb4d,
title = "Bayesian body localization using mixture of nonlinear shape models",
abstract = "We present a 2D model-based approach to localizing human body in images viewed from arbitrary and unknown angles. The central component is a statistical shape representation of the nonrigid and articulated body contours, where a nonlinear deformation is decomposed based on the concept of parts. Several image cues are combined to relate the body configuration to the observed image, with self-occlusion explicitly treated. To accommodate large viewpoint changes, a mixture of view-dependent models is employed. Inference is done by direct sampling of the posterior mixture, using Sequential Monte Carlo (SMC) simulation enhanced with annealing and kernel move. The fitting method is independent of the number of mixture components, and does not require the preselection of a {"}correct{"} viewpoint. The models were trained on a large number of interactively labeled gait images. Preliminary tests demonstrated the feasibility of the proposed approach.",
author = "Jiayong Zhang and Robert Collins and Yanxi Liu",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/ICCV.2005.45",
language = "English (US)",
isbn = "076952334X",
series = "Proceedings of the IEEE International Conference on Computer Vision",
pages = "725--732",
booktitle = "Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005",

}

Zhang, J, Collins, R & Liu, Y 2005, Bayesian body localization using mixture of nonlinear shape models. in Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005., 1541325, Proceedings of the IEEE International Conference on Computer Vision, vol. I, pp. 725-732, Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005, Beijing, China, 10/17/05. https://doi.org/10.1109/ICCV.2005.45

Bayesian body localization using mixture of nonlinear shape models. / Zhang, Jiayong; Collins, Robert; Liu, Yanxi.

Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. 2005. p. 725-732 1541325 (Proceedings of the IEEE International Conference on Computer Vision; Vol. I).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Bayesian body localization using mixture of nonlinear shape models

AU - Zhang, Jiayong

AU - Collins, Robert

AU - Liu, Yanxi

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We present a 2D model-based approach to localizing human body in images viewed from arbitrary and unknown angles. The central component is a statistical shape representation of the nonrigid and articulated body contours, where a nonlinear deformation is decomposed based on the concept of parts. Several image cues are combined to relate the body configuration to the observed image, with self-occlusion explicitly treated. To accommodate large viewpoint changes, a mixture of view-dependent models is employed. Inference is done by direct sampling of the posterior mixture, using Sequential Monte Carlo (SMC) simulation enhanced with annealing and kernel move. The fitting method is independent of the number of mixture components, and does not require the preselection of a "correct" viewpoint. The models were trained on a large number of interactively labeled gait images. Preliminary tests demonstrated the feasibility of the proposed approach.

AB - We present a 2D model-based approach to localizing human body in images viewed from arbitrary and unknown angles. The central component is a statistical shape representation of the nonrigid and articulated body contours, where a nonlinear deformation is decomposed based on the concept of parts. Several image cues are combined to relate the body configuration to the observed image, with self-occlusion explicitly treated. To accommodate large viewpoint changes, a mixture of view-dependent models is employed. Inference is done by direct sampling of the posterior mixture, using Sequential Monte Carlo (SMC) simulation enhanced with annealing and kernel move. The fitting method is independent of the number of mixture components, and does not require the preselection of a "correct" viewpoint. The models were trained on a large number of interactively labeled gait images. Preliminary tests demonstrated the feasibility of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=33745934480&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745934480&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2005.45

DO - 10.1109/ICCV.2005.45

M3 - Conference contribution

SN - 076952334X

SN - 9780769523347

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 725

EP - 732

BT - Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005

ER -

Zhang J, Collins R, Liu Y. Bayesian body localization using mixture of nonlinear shape models. In Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. 2005. p. 725-732. 1541325. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2005.45