Human pose as calibration pattern: 3D human pose estimation with multiple unsynchronized and uncalibrated cameras

Kosuke Takahashi, Dan Mikami, Mariko Isogawa, Hideaki Kimata

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

14 Citations (Scopus)

Abstract

This paper proposes a novel algorithm of estimating 3D human pose from multi-view videos captured by unsynchronized and uncalibrated cameras. In a such configuration, the conventional vision-based approaches utilize detected 2D features of common 3D points for synchronization and camera pose estimation, however, they sometimes suffer from difficulties of feature correspondences in case of wide baselines. For such cases, the proposed method focuses on that the projections of human joints can be associated each other robustly even in wide baseline videos and utilizes them as the common reference points. To utilize the projections of joint as the corresponding points, they should be detected in the images, however, these 2D joint sometimes include detection errors which make the estimation unstable. For dealing with such errors, the proposed method introduces two ideas. The first idea is to relax the reprojection errors for avoiding optimizing to noised observations. The second idea is to introduce an geometric constraint on the prior knowledge that the reference points consists of human joints. We demonstrate the performance of the proposed algorithm of synchronization and pose estimation with qualitative and quantitative evaluations using synthesized and real data.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
PublisherIEEE Computer Society
Pages1856-1863
Number of pages8
ISBN (Electronic)9781538661000
DOIs
Publication statusPublished - 2018 Dec 13
Externally publishedYes
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States
Duration: 2018 Jun 182018 Jun 22

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2018-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Other

Other31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Country/TerritoryUnited States
CitySalt Lake City
Period18/6/1818/6/22

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Human pose as calibration pattern: 3D human pose estimation with multiple unsynchronized and uncalibrated cameras'. Together they form a unique fingerprint.

Cite this