Multi‐view pose estimation with mixtures of parts and adaptive viewpoint selection

Multi‐view pose estimation with mixtures of parts and adaptive viewpoint selection

We propose a new method for human pose estimation which leverages information from multiple views to impose a strong prior on articulated pose. The novelty of the method concerns the types of coherence modelled. Consistency is maximised over the different views through different terms modelling clas...

Full description

Bibliographic Details
Main Authors: Emre Dogan, Gonen Eren, Christian Wolf, Eric Lombardi, Atilla Baskurt
Format: Article
Language:English
Published: Wiley 2018-06-01
Series:IET Computer Vision
Subjects:
multiview pose estimation
adaptive viewpoint selection
human pose estimation
geometric information
HumanEva
Utrecht multiperson motion
Online Access:https://doi.org/10.1049/iet-cvi.2017.0146

Internet

https://doi.org/10.1049/iet-cvi.2017.0146

Similar Items