Open AccessMulti‐view pose estimation with mixtures of parts and adaptive viewpoint selection
Author(s) -
Dogan Emre,
Eren Gonen,
Wolf Christian,
Lombardi Eric,
Baskurt Atilla
Publication year - 2018
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2017.0146
Subject(s) - pose , coherence (philosophical gambling strategy) , novelty , computer science , artificial intelligence , consistency (knowledge bases) , estimation , selection (genetic algorithm) , machine learning , computer vision , pattern recognition (psychology) , mathematics , statistics , philosophy , theology , management , economics
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 classical geometric information (coherence of the resulting poses) as well as appearance information which is modelled as latent variables in the global energy function. Moreover, adequacy of each view is assessed and their contributions are adjusted accordingly. Experiments on the HumanEva and Utrecht multi‐person motion datasets show that the proposed method significantly decreases the estimation error compared to single‐view results.