Single image 3D human pose estimation from noisy observations

E. Simo-Serra*, A. Ramisa, G. Alenya, C. Torras, F. Moreno-Noguer

*この研究の対応する著者

研究成果: Conference contribution

93 被引用数 (Scopus)

抄録

Markerless 3D human pose detection from a single image is a severely underconstrained problem because different 3D poses can have similar image projections. In order to handle this ambiguity, current approaches rely on prior shape models that can only be correctly adjusted if 2D image features are accurately detected. Unfortunately, although current 2D part detector algorithms have shown promising results, they are not yet accurate enough to guarantee a complete disambiguation of the 3D inferred shape. In this paper, we introduce a novel approach for estimating 3D human pose even when observations are noisy. We propose a stochastic sampling strategy to propagate the noise from the image plane to the shape space. This provides a set of ambiguous 3D shapes, which are virtually undistinguishable from their image projections. Disambiguation is then achieved by imposing kinematic constraints that guarantee the resulting pose resembles a 3D human shape. We validate the method on a variety of situations in which state-of-the-art 2D detectors yield either inaccurate estimations or partly miss some of the body parts.

本文言語English
ホスト出版物のタイトル2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
ページ2673-2680
ページ数8
DOI
出版ステータスPublished - 2012
外部発表はい
イベント2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 - Providence, RI, United States
継続期間: 2012 6月 162012 6月 21

出版物シリーズ

名前Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN(印刷版)1063-6919

Other

Other2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
国/地域United States
CityProvidence, RI
Period12/6/1612/6/21

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Single image 3D human pose estimation from noisy observations」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル