Comparative evaluation of 3D pose estimation of industrial objects in RGB pointclouds
(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:
https://lup.lub.lu.se/record/dd23bac8-7962-4447-8bba-f4c1dff0bb37
- author
- Großmann, Bjarne ; Siam, Mennatullah and Krüger, Volker LU
- publishing date
- 2015-06-19
- 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
- 978-3-319-20903-6
- 978-3-319-20904-3
- 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
- 2024-04-30 08:03:59
@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 = {{978-3-319-20903-6}}, issn = {{0302-9743}}, keywords = {{Feature descriptor; Performance evaluation; Pointcloud registration; Pose estimation; Robot vision}}, 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}}, }