Point cloud human pose estimation using capsule networks
Date
2021
Authors
Onbysh, Oleksandr
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Human pose estimation based on points cloud is an emerging field that develops
with 3D scanning devices’ popularity. Build-in LiDAR technology in mobile phones
and a growing VR market creates a demand for lightweight and accurate models
for 3D point cloud. Widely advanced deep learning tools are mainly used for structured
data, and they face new challenges in unstructured 3D space. Recent research
on capsule networks proves that this type of model outperforms classical CNN architectures
in tasks that require viewpoint invariance from the model. Thus capsule
networks challenge multiple issues of classic CNNs like preserving the orientation
and spatial relationship of extracted features, which could significantly improve the
3D points cloud classification task’s performance.
The project’s objective is to experimentally assess the applicability of capsule
neural network architecture to the task of point cloud human pose estimation and
measure performance on non-synthetic data. Additionally, measure noise sustainability
of capsule networks for 3D data compared to regular models. Compare models’
performance with restricted amount of training data.
Description
Keywords
point cloud, capsule network, human pose estimation, noisy data
Citation
Onbysh, Oleksandr. Point cloud human pose estimation using capsule networks / Oleksandr Onbysh; Supervisor: Andrii Babii; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2021. – 53 p.: ill.