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

84 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
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