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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-06-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2017.0146 |
| Summary: | 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. |
|---|---|
| ISSN: | 1751-9632 1751-9640 |