Ensemble of 6 DoF Pose estimation from state-of-the-art deep methods.

Ibon Merino; Jon Azpiazu; Anthony Remazeilles; Basilio Sierra

doi:10.1016/j.neucom.2023.126270

Ensemble of 6 DoF Pose estimation from state-of-the-art deep methods.

Ibon Merino^*, Jon Azpiazu, Anthony Remazeilles, Basilio Sierra

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

Deep learning methods have revolutionized computer vision since the appearance of AlexNet in 2012. Nevertheless, 6 degrees of freedom pose estimation is still a difficult task to perform precisely. Therefore, we propose 2 ensemble techniques to refine poses from different deep learning 6DoF pose estimation models. The first technique, merge ensemble, combines the outputs of the base models geometrically. In the second, stacked generalization, a machine learning model is trained using the outputs of the base models and outputs the refined pose. The merge method improves the performance of the base models on LMO and YCB-V datasets and performs better on the pose estimation task than the stacking strategy.

Original language	English
Article number	126270
Journal	Neurocomputing
Volume	541
DOIs	https://doi.org/10.1016/j.neucom.2023.126270
Publication status	Published - 7 Jul 2023

Funding

This paper has been supported by the project PROFLOW under the Basque program ELKARTEK, grant agreement No. KK-2022/00024.

Keywords

Deep learning
Ensemble
Pose estimation
Stacked generalization

Access to Document

10.1016/j.neucom.2023.126270

Cite this

@article{0acfe959507d4283bd707007a2700f6d,

title = "Ensemble of 6 DoF Pose estimation from state-of-the-art deep methods.",

abstract = "Deep learning methods have revolutionized computer vision since the appearance of AlexNet in 2012. Nevertheless, 6 degrees of freedom pose estimation is still a difficult task to perform precisely. Therefore, we propose 2 ensemble techniques to refine poses from different deep learning 6DoF pose estimation models. The first technique, merge ensemble, combines the outputs of the base models geometrically. In the second, stacked generalization, a machine learning model is trained using the outputs of the base models and outputs the refined pose. The merge method improves the performance of the base models on LMO and YCB-V datasets and performs better on the pose estimation task than the stacking strategy.",

keywords = "Deep learning, Ensemble, Pose estimation, Stacked generalization",

author = "Ibon Merino and Jon Azpiazu and Anthony Remazeilles and Basilio Sierra",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors",

year = "2023",

month = jul,

day = "7",

doi = "10.1016/j.neucom.2023.126270",

language = "English",

volume = "541",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier",

}

TY - JOUR

T1 - Ensemble of 6 DoF Pose estimation from state-of-the-art deep methods.

AU - Merino, Ibon

AU - Azpiazu, Jon

AU - Remazeilles, Anthony

AU - Sierra, Basilio

PY - 2023/7/7

Y1 - 2023/7/7

N2 - Deep learning methods have revolutionized computer vision since the appearance of AlexNet in 2012. Nevertheless, 6 degrees of freedom pose estimation is still a difficult task to perform precisely. Therefore, we propose 2 ensemble techniques to refine poses from different deep learning 6DoF pose estimation models. The first technique, merge ensemble, combines the outputs of the base models geometrically. In the second, stacked generalization, a machine learning model is trained using the outputs of the base models and outputs the refined pose. The merge method improves the performance of the base models on LMO and YCB-V datasets and performs better on the pose estimation task than the stacking strategy.

AB - Deep learning methods have revolutionized computer vision since the appearance of AlexNet in 2012. Nevertheless, 6 degrees of freedom pose estimation is still a difficult task to perform precisely. Therefore, we propose 2 ensemble techniques to refine poses from different deep learning 6DoF pose estimation models. The first technique, merge ensemble, combines the outputs of the base models geometrically. In the second, stacked generalization, a machine learning model is trained using the outputs of the base models and outputs the refined pose. The merge method improves the performance of the base models on LMO and YCB-V datasets and performs better on the pose estimation task than the stacking strategy.

KW - Deep learning

KW - Ensemble

KW - Pose estimation

KW - Stacked generalization

UR - http://www.scopus.com/inward/record.url?scp=85154049457&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2023.126270

DO - 10.1016/j.neucom.2023.126270

M3 - Article

AN - SCOPUS:85154049457

SN - 0925-2312

VL - 541

JO - Neurocomputing

JF - Neurocomputing

M1 - 126270

ER -

Ensemble of 6 DoF Pose estimation from state-of-the-art deep methods.

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this