Multi‐view pose estimation with mixtures of parts and adaptive viewpoint selection
Authors:
Open Access
- 21 December 2017
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 12 (4) , 403-411
Abstract
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.Keywords
All Related Versions
Funding Information
- Galatasaray Üniversitesi (BAP 14.401.001)
This publication has 32 references indexed in Scilit:
- Accurate Human Pose Estimation by Aggregating Multiple Pose Hypotheses Using Modified Kernel Density ApproximationIEEE Signal Processing Letters, 2014
- DeepPose: Human Pose Estimation via Deep Neural Networks2014
- Body Parts Dependent Joint Regressors for Human Pose Estimation in Still ImagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Poselet Conditioned Pictorial Structures2013
- Multi-view Body Part Recognition with Random Forests2013
- Multi-view Pictorial Structures for 3D Human Pose Estimation2013
- Appearance Sharing for Collective Human Pose Estimation2013
- Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief PropagationInternational Journal of Computer Vision, 2011
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human MotionInternational Journal of Computer Vision, 2009
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005