6D Pose Estimation of Transparent Object from Single RGB Image
Transparent objects are one of the most common objects in everyday life. Estimating pose of these objects are required to pick and manipulate such objects. However, due to the absorption and refraction of light, it is hard to capture depth im- age of transparent object. In this paper, we address thi...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
FRUCT
2019-11-01
|
Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
Subjects: | |
Online Access: | https://fruct.org/publications/acm25/files/Bya.pdf
|
id |
doaj-c958f65d195f464db572dbecf20e3602 |
---|---|
record_format |
Article |
spelling |
doaj-c958f65d195f464db572dbecf20e36022020-11-25T02:16:36ZengFRUCTProceedings of the XXth Conference of Open Innovations Association FRUCT2305-72542343-07372019-11-01622254444476D Pose Estimation of Transparent Object from Single RGB ImageMunkhtulga Byambaa0Gou Koutaki1Lodoiravsal Choimaa2Kumamoto University, Kumamoto, JapanKumamoto University, Kumamoto, JapanNational University of Mongolia, Ulaanbaatar, MongoliaTransparent objects are one of the most common objects in everyday life. Estimating pose of these objects are required to pick and manipulate such objects. However, due to the absorption and refraction of light, it is hard to capture depth im- age of transparent object. In this paper, we address this problem using synthetic dataset to train deep neural network and estimate pose of known transparent objects. Synthetic dataset contains depth map of transparent object which we created in realistic looking environment. Also combining domain randomized and photorealistic images, we create desired amount of annotated data in order to network operate successfully against real world data. We conducted experiment on 3D printed transparent objects in the real environment. For future work, we are planning to build random bin picking system for transparent object.https://fruct.org/publications/acm25/files/Bya.pdf pose estimationtransparent objectsynthetic datadeep neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Munkhtulga Byambaa Gou Koutaki Lodoiravsal Choimaa |
spellingShingle |
Munkhtulga Byambaa Gou Koutaki Lodoiravsal Choimaa 6D Pose Estimation of Transparent Object from Single RGB Image Proceedings of the XXth Conference of Open Innovations Association FRUCT pose estimation transparent object synthetic data deep neural network |
author_facet |
Munkhtulga Byambaa Gou Koutaki Lodoiravsal Choimaa |
author_sort |
Munkhtulga Byambaa |
title |
6D Pose Estimation of Transparent Object from Single RGB Image |
title_short |
6D Pose Estimation of Transparent Object from Single RGB Image |
title_full |
6D Pose Estimation of Transparent Object from Single RGB Image |
title_fullStr |
6D Pose Estimation of Transparent Object from Single RGB Image |
title_full_unstemmed |
6D Pose Estimation of Transparent Object from Single RGB Image |
title_sort |
6d pose estimation of transparent object from single rgb image |
publisher |
FRUCT |
series |
Proceedings of the XXth Conference of Open Innovations Association FRUCT |
issn |
2305-7254 2343-0737 |
publishDate |
2019-11-01 |
description |
Transparent objects are one of the most common objects in everyday life. Estimating pose of these objects are required to pick and manipulate such objects. However, due to the absorption and refraction of light, it is hard to capture depth im- age of transparent object. In this paper, we address this problem using synthetic dataset to train deep neural network and estimate pose of known transparent objects. Synthetic dataset contains depth map of transparent object which we created in realistic looking environment. Also combining domain randomized and photorealistic images, we create desired amount of annotated data in order to network operate successfully against real world data. We conducted experiment on 3D printed transparent objects in the real environment. For future work, we are planning to build random bin picking system for transparent object. |
topic |
pose estimation transparent object synthetic data deep neural network |
url |
https://fruct.org/publications/acm25/files/Bya.pdf
|
work_keys_str_mv |
AT munkhtulgabyambaa 6dposeestimationoftransparentobjectfromsinglergbimage AT goukoutaki 6dposeestimationoftransparentobjectfromsinglergbimage AT lodoiravsalchoimaa 6dposeestimationoftransparentobjectfromsinglergbimage |
_version_ |
1724890335608307712 |