Advanced

Comparative evaluation of 3D pose estimation of industrial objects in RGB pointclouds

Großmann, Bjarne ; Siam, Mennatullah and Krüger, Volker LU (2015) 10th International Conference on Computer Vision Systems, ICVS 2015 In Lecture Notes in Computer Science 9163. p.329-342
Abstract
3D pose estimation is a crucial element for enabling robots to work in industrial environment to perform tasks like bin-picking or depalletizing. Even though there exist various pose estimation algorithms, they usually deal with common daily objects applied in lab environments. However, coping with real-world industrial objects is a much harder challenge for most pose estimation techniques due to the difficult material and structural properties of those objects. A comparative evaluation of pose estimation algorithms in regard to these object characteristics has yet to be done. This paper aims to provide a description and evaluation of selected state-of-the-art pose estimation techniques to investigate their object-related performance in... (More)
3D pose estimation is a crucial element for enabling robots to work in industrial environment to perform tasks like bin-picking or depalletizing. Even though there exist various pose estimation algorithms, they usually deal with common daily objects applied in lab environments. However, coping with real-world industrial objects is a much harder challenge for most pose estimation techniques due to the difficult material and structural properties of those objects. A comparative evaluation of pose estimation algorithms in regard to these object characteristics has yet to be done. This paper aims to provide a description and evaluation of selected state-of-the-art pose estimation techniques to investigate their object-related performance in terms of time and accuracy. The evaluation shows that there is indeed not a general algorithm which solves the task for all different objects, but it outlines the issues that real-world application have to deal with and what the strengths and weaknesses of the different pose estimation approaches are. (Less)
Abstract (Swedish)
3D pose estimation is a crucial element for enabling robots to work in industrial environment to perform tasks like bin-picking or depalletizing. Even though there exist various pose estimation algorithms, they usually deal with common daily objects applied in lab environments. However, coping with real-world industrial objects is a much harder challenge for most pose estimation techniques due to the difficult material and structural properties of those objects. A comparative evaluation of pose estimation algorithms in regard to these object characteristics has yet to be done. This paper aims to provide a description and evaluation of selected state-of-the-art pose estimation techniques to investigate their object-related performance in... (More)
3D pose estimation is a crucial element for enabling robots to work in industrial environment to perform tasks like bin-picking or depalletizing. Even though there exist various pose estimation algorithms, they usually deal with common daily objects applied in lab environments. However, coping with real-world industrial objects is a much harder challenge for most pose estimation techniques due to the difficult material and structural properties of those objects. A comparative evaluation of pose estimation algorithms in regard to these object characteristics has yet to be done. This paper aims to provide a description and evaluation of selected state-of-the-art pose estimation techniques to investigate their object-related performance in terms of time and accuracy. The evaluation shows that there is indeed not a general algorithm which solves the task for all different objects, but it outlines the issues that real-world application have to deal with and what the strengths and weaknesses of the different pose estimation approaches are. (Less)
Please use this url to cite or link to this publication:
author
; and
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Feature descriptor, Performance evaluation, Pointcloud registration, Pose estimation, Robot vision
host publication
Computer Vision Systems
series title
Lecture Notes in Computer Science
editor
Nalpantidis, Lazaros ; Krüger, Volker ; Eklundh, Jan-Olof and Gasteratos, Antonios
volume
9163
pages
14 pages
publisher
Springer
conference name
10th International Conference on Computer Vision Systems, ICVS 2015
conference location
Copenhagen, Denmark
conference dates
2015-07-06 - 2015-07-09
external identifiers
  • scopus:84948976803
ISSN
0302-9743
1611-3349
ISBN
978-3-319-20904-3
978-3-319-20903-6
DOI
10.1007/978-3-319-20904-3_30
language
English
LU publication?
no
id
dd23bac8-7962-4447-8bba-f4c1dff0bb37
date added to LUP
2019-05-16 21:28:45
date last changed
2020-07-16 03:23:50
@inproceedings{dd23bac8-7962-4447-8bba-f4c1dff0bb37,
  abstract     = {3D pose estimation is a crucial element for enabling robots to work in industrial environment to perform tasks like bin-picking or depalletizing. Even though there exist various pose estimation algorithms, they usually deal with common daily objects applied in lab environments. However, coping with real-world industrial objects is a much harder challenge for most pose estimation techniques due to the difficult material and structural properties of those objects. A comparative evaluation of pose estimation algorithms in regard to these object characteristics has yet to be done. This paper aims to provide a description and evaluation of selected state-of-the-art pose estimation techniques to investigate their object-related performance in terms of time and accuracy. The evaluation shows that there is indeed not a general algorithm which solves the task for all different objects, but it outlines the issues that real-world application have to deal with and what the strengths and weaknesses of the different pose estimation approaches are.},
  author       = {Großmann, Bjarne and Siam, Mennatullah and Krüger, Volker},
  booktitle    = {Computer Vision Systems},
  editor       = {Nalpantidis, Lazaros and Krüger, Volker and Eklundh, Jan-Olof and Gasteratos, Antonios},
  isbn         = {978-3-319-20904-3},
  issn         = {0302-9743},
  language     = {eng},
  month        = {06},
  pages        = {329--342},
  publisher    = {Springer},
  series       = {Lecture Notes in Computer Science},
  title        = {Comparative evaluation of 3D pose estimation of industrial objects in RGB pointclouds},
  url          = {http://dx.doi.org/10.1007/978-3-319-20904-3_30},
  doi          = {10.1007/978-3-319-20904-3_30},
  volume       = {9163},
  year         = {2015},
}