Hidden Markov Models for Pose Estimation

László Czúni, Amr M. Nagy

2020

Abstract

Estimation of the pose of objects is essential in order to interact with the real world in many applications such as robotics, augmented reality or autonomous driving. The key challenges we must face in the recognition of objects and their pose is due to the diversity of their visual appearance in addition to the complexity of the environment, the variations of illumination, and possibilities of occlusions. We have previously shown that Hidden Markov Models (HMMs) can improve the recognition of objects even with the help of weak object classifiers if orientation information is also utilized during the recognition process. In this paper we describe our first attempts when we apply HMMs to improve the pose selection of elementary convolutional neural networks (CNNs).

Paper Citation

in Harvard Style

Czúni L. and Nagy A. (2020). Hidden Markov Models for Pose Estimation. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 598-603. DOI: 10.5220/0009357505980603

in Bibtex Style

@conference{visapp20,
author={László Czúni and Amr M. Nagy},
title={Hidden Markov Models for Pose Estimation},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={598-603},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009357505980603},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Hidden Markov Models for Pose Estimation
SN - 978-989-758-402-2
AU - Czúni L.
AU - Nagy A.
PY - 2020
SP - 598
EP - 603
DO - 10.5220/0009357505980603
PB - SciTePress