Skip to Main content Skip to Navigation
Journal articles

Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network

Abstract : This paper addresses the problems of the graphical-based human pose estimation in still images, including the diversity of appearances and confounding background clutter. We present a new architecture for estimating human pose using a Convolutional Neural Network (CNN). Firstly, a Relative Mixture Deformable Model (RMDM) is defined by each pair of connected parts to compute the relative spatial information in the graphical model. Secondly, a Local Multi-Resolution Convolutional Neural Network (LMR-CNN) is proposed to train and learn the multi-scale representation of each body parts by combining different levels of part context. Thirdly, a LMR-CNN based hierarchical model is defined to explore the context information of limb parts. Finally, the experimental results demonstrate the effectiveness of the proposed deep learning approach for human pose estimation.
Document type :
Journal articles
Complete list of metadata

https://hal-utt.archives-ouvertes.fr/hal-03320694
Contributor : Jean-Baptiste Vu Van Connect in order to contact the contributor
Submitted on : Monday, August 16, 2021 - 12:01:33 PM
Last modification on : Wednesday, October 13, 2021 - 7:16:03 PM

Links full text

Identifiers

Collections

UTT | CNRS

Citation

Aichun Zhu, Tian Wang, Hichem Snoussi. Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network. AIP Advances, American Institute of Physics- AIP Publishing LLC, 2018, 8 (3), pp.035215. ⟨10.1063/1.5024463⟩. ⟨hal-03320694⟩

Share

Metrics

Record views

16