Object 6 Degrees of Freedom Pose Estimation with Mask-R-CNN and Virtual Training

DOI

10.2991/jrnal.k.201215.008How to use a DOI?

Keywords

Pose estimation; deep-learning; keypoints localization; instance segmentation; virtual training; factory automation

Abstract

Pose estimation algorithms’ goal is to find the position and the orientation of an object in space, given only an image. This task may be complex, especially in an uncontrolled environment with several parameters that can vary, like the object texture, background or the lightning conditions. Most algorithms performing pose estimation use deep learning methods. However, it may be difficult to create dataset to train such kind of models. In this paper we developed a new algorithm robust to a high variability of conditions using instance segmentation of the image and trainable on a virtual dataset. This system performs semantic keypoints based pose estimation without considering background, lighting or texture changes on the object.

Copyright

© 2020 The Authors. Published by Atlantis Press B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Victor Pujolle
AU  - Eiji Hayashi
PY  - 2020
DA  - 2020/12/28
TI  - Object 6 Degrees of Freedom Pose Estimation with Mask-R-CNN and Virtual Training
JO  - Journal of Robotics, Networking and Artificial Life
SP  - 249
EP  - 252
VL  - 7
IS  - 4
SN  - 2352-6386
UR  - https://doi.org/10.2991/jrnal.k.201215.008
DO  - 10.2991/jrnal.k.201215.008
ID  - Pujolle2020
ER  -