Fast human pose estimation using appearance and motion via multi-dimensional boosting regression

Alessandro Bissacco, Ming Hsuan Yang, Stefano Soatto

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

81 Citations (Scopus)

Abstract

We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our algorithm can be viewed as a fast initialization step for human body trackers, or as a tracker itself. We extend gradient boosting techniques to learn a multi-dimensional map from (rotated and scaled) Haar features to the entire set of joint angles representing the full body pose. We test our approach by learning a map from image patches to body joint angles from synchronized video and motion capture walking data. We show how our technique enables learning an efficient real-time pose estimator, validated on publicly available datasets.

Original languageEnglish
Title of host publication2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
DOIs
Publication statusPublished - 2007 Oct 11
Event2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07 - Minneapolis, MN, United States
Duration: 2007 Jun 172007 Jun 22

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Other

Other2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
CountryUnited States
CityMinneapolis, MN
Period07/6/1707/6/22

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Bissacco, A., Yang, M. H., & Soatto, S. (2007). Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. In 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07 [4270154] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2007.383129
Bissacco, Alessandro ; Yang, Ming Hsuan ; Soatto, Stefano. / Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07. 2007. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{a5ff3098711c4a05a230498a80f260d0,
title = "Fast human pose estimation using appearance and motion via multi-dimensional boosting regression",
abstract = "We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our algorithm can be viewed as a fast initialization step for human body trackers, or as a tracker itself. We extend gradient boosting techniques to learn a multi-dimensional map from (rotated and scaled) Haar features to the entire set of joint angles representing the full body pose. We test our approach by learning a map from image patches to body joint angles from synchronized video and motion capture walking data. We show how our technique enables learning an efficient real-time pose estimator, validated on publicly available datasets.",
author = "Alessandro Bissacco and Yang, {Ming Hsuan} and Stefano Soatto",
year = "2007",
month = "10",
day = "11",
doi = "10.1109/CVPR.2007.383129",
language = "English",
isbn = "1424411807",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
booktitle = "2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07",

}

Bissacco, A, Yang, MH & Soatto, S 2007, Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. in 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07., 4270154, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07, Minneapolis, MN, United States, 07/6/17. https://doi.org/10.1109/CVPR.2007.383129

Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. / Bissacco, Alessandro; Yang, Ming Hsuan; Soatto, Stefano.

2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07. 2007. 4270154 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

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

TY - GEN

T1 - Fast human pose estimation using appearance and motion via multi-dimensional boosting regression

AU - Bissacco, Alessandro

AU - Yang, Ming Hsuan

AU - Soatto, Stefano

PY - 2007/10/11

Y1 - 2007/10/11

N2 - We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our algorithm can be viewed as a fast initialization step for human body trackers, or as a tracker itself. We extend gradient boosting techniques to learn a multi-dimensional map from (rotated and scaled) Haar features to the entire set of joint angles representing the full body pose. We test our approach by learning a map from image patches to body joint angles from synchronized video and motion capture walking data. We show how our technique enables learning an efficient real-time pose estimator, validated on publicly available datasets.

AB - We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our algorithm can be viewed as a fast initialization step for human body trackers, or as a tracker itself. We extend gradient boosting techniques to learn a multi-dimensional map from (rotated and scaled) Haar features to the entire set of joint angles representing the full body pose. We test our approach by learning a map from image patches to body joint angles from synchronized video and motion capture walking data. We show how our technique enables learning an efficient real-time pose estimator, validated on publicly available datasets.

UR - http://www.scopus.com/inward/record.url?scp=34948844078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34948844078&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2007.383129

DO - 10.1109/CVPR.2007.383129

M3 - Conference contribution

AN - SCOPUS:34948844078

SN - 1424411807

SN - 9781424411801

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

BT - 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07

ER -

Bissacco A, Yang MH, Soatto S. Fast human pose estimation using appearance and motion via multi-dimensional boosting regression. In 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07. 2007. 4270154. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2007.383129