liu.seSearch for publications in DiVA
Change search
Link to record
Permanent link

Direct link
BETA
Viksten, Fredrik
Publications (10 of 17) Show all publications
Nordberg, K. & Viksten, F. (2010). A local geometry based descriptor for 3D data: Addendum on rank and segment extraction.
Open this publication in new window or tab >>A local geometry based descriptor for 3D data: Addendum on rank and segment extraction
2010 (English)Report (Other academic)
Abstract [en]

This document is an addendum to the main text in A local geometry-based descriptor for 3D data applied to object pose estimation by Fredrik Viksten and Klas Nordberg. This addendum gives proofs for propositions stated in the main document. This addendum also details how to extract information from the fourth order tensor refered to as S22 in the main document.

Series
LiTH-ISY-R, ISSN 1400-3902 ; 2951
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-57329 (URN)
Available from: 2010-06-16 Created: 2010-06-16 Last updated: 2018-01-12Bibliographically approved
Viksten, F. & Nordberg, K. (2010). A Local Geometry-Based Descriptor for 3D Data Applied to Object Pose Estimation.
Open this publication in new window or tab >>A Local Geometry-Based Descriptor for 3D Data Applied to Object Pose Estimation
2010 (English)Manuscript (preprint) (Other academic)
Abstract [en]

A local descriptor for 3D data, the scene tensor, is presentedtogether with novel applications.  It can describe multiple planarsegments in a local 3D region; for the case of up to three segments itis possible to recover the geometry of the local region in terms of thesize, position and orientation of each of the segments from thedescriptor. In the setting of range data, this property makes thedescriptor unique compared to other popular local descriptors, such asspin images or point signatures.  The estimation of the descriptor canbe based on 3D orientation tensors that, for example, can be computeddirectly from surface normals but the representation itself does notdepend on a specific estimation method and can also be applied to othertypes of 3D data, such as motion stereo. A series of experiments onboth real and synthetic range data show that the proposedrepresentation can be used as a interest point detector with highrepeatability. Further, the experiments show that, at such detectedpoints, the local geometric structure can be robustly recovered, evenin the presence of noise. Last we expand a framework for object poseestimation, based on the scene tensor and previously appliedsuccessfully on 2D image data, to work also on range data. Poseestimation from real range data shows that there are advantages oversimilar descriptors in 2D and that use of range data gives superiorperformance.

Keywords
3D analysis, local descriptor, tensor, range data
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-57328 (URN)LiTH-ISY-R-2951 (ISRN)
Note

See also the addendum which is found at http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-57329

Available from: 2010-06-16 Created: 2010-06-16 Last updated: 2018-01-12Bibliographically approved
Viksten, F. (2010). Local Features for Range and Vision-Based Robotic Automation. (Doctoral dissertation). Linköping: Linköping University Electronic Press
Open this publication in new window or tab >>Local Features for Range and Vision-Based Robotic Automation
2010 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Robotic automation has been a part of state-of-the-art manufacturing for many decades. Robotic manipulators are used for such tasks as welding, painting, pick and place tasks etc. Robotic manipulators are quite flexible and adaptable to new tasks, but a typical robot-based production cell requires extensive specification of the robot motion and construction of tools and fixtures for material handling. This incurs a large effort both in time and monetary expenses. The task of a vision system in this setting is to simplify the control and guidance of the robot and to reduce the need for supporting material handling machinery.

This dissertation examines performance and properties of the current state-of-the-art local features within the setting of object pose estimation. This is done through an extensive set of experiments replicating various potential problems to which a vision system in a robotic cell could be subjected. The dissertation presents new local features which are shown to increase the performance of object pose estimation. A new local descriptor details how to use log-polar sampled image patches for truly rotational invariant matching. This representation is also extended to use a scale-space interest point detector which in turn makes it very competitive in our experiments. A number of variations of already available descriptors are constructed resulting in new and competitive features, among them a scale-space based Patch-duplet.

In this dissertation a successful vision-based object pose estimation system is extended for multi-cue integration, yielding increased robustness and accuracy. Robustness is increased through algorithmic multi-cue integration, combining the individual strengths of multiple local features. Increased accuracy is achieved by utilizing manipulator movement and applying temporal multi-cue integration. This is implemented using a real flexible robotic manipulator arm.

Besides work done on local features for ordinary image data a number of local features for range data has also been developed. This dissertation describes the theory behind and the application of the scene tensor to the problem of object pose estimation. The scene tensor is a fourth order tensor representation using projective geometry. It is shown how to use the scene tensor as a detector as well as how to apply it to the task of object pose estimation. The object pose estimation system is extended to work with 3D data.

A novel way of handling sampling of range data when constructing a detector is discussed. A volume rasterization method is presented and the classic Harris detector is adapted to it. Finally, a novel region detector, called Maximally Robust Range Regions, is presented. All developed detectors are compared in a detector repeatability test.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2010. p. 81
Series
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 1325
Keywords
Local features, object pose estimation, range data
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-57333 (URN)978-91-7393-362-9 (ISBN)
Public defence
2010-09-09, Glashuset, House B, entrance 25,, Campus Valla, Linköpings universitet, Linköping, 13:00 (English)
Opponent
Supervisors
Available from: 2010-06-17 Created: 2010-06-17 Last updated: 2018-01-12Bibliographically approved
Viksten, F., Forssén, P.-E., Johansson, B. & Moe, A. (2010). Local Image Descriptors for Full 6 Degree-of-Freedom Object Pose Estimation and Recognition.
Open this publication in new window or tab >>Local Image Descriptors for Full 6 Degree-of-Freedom Object Pose Estimation and Recognition
2010 (English)Article in journal (Refereed) Submitted
Abstract [en]

Recent years have seen advances in the estimation of full 6 degree-of-freedom object pose from a single 2D image. These advances have often been presented as a result of, or together with, a new local image feature type. This paper examines how the pose accuracy and recognition robustness for such a system varies with choice of feature type. This is done by evaluating a full 6 degree-of-freedom pose estimation system for 17 different combinations of local descriptors and detectors. The evaluation is done on data sets with photos of challenging 3D objects with simple and complex backgrounds and varying illumination conditions. We examine the performance of the system under varying levels of object occlusion and we find that many features allow considerable object occlusion. From the experiments we can conclude that duplet features, that use pairs of interest points, improve pose estimation accuracy, compared to single point features. Interestingly, we can also show that many features previously used for recognition and wide-baseline stereo are unsuitable for pose estimation, one notable example are the affine covariant features that have been proven quite successful in other applications. The data sets and their ground truths are available on the web to allow future comparison with novel algorithms.

Keywords
bin picking, pose estimation, local features
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-57330 (URN)
Note
This is an extension of http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-44894Available from: 2010-06-16 Created: 2010-06-16 Last updated: 2018-01-12
Viksten, F. & Forssén, P.-E. (2010). Maximally Robust Range Regions.
Open this publication in new window or tab >>Maximally Robust Range Regions
2010 (English)Report (Other academic)
Abstract [en]

In this work we present a region detector, an adaptation to range data of the popular Maximally Stable Extremal Regions (MSER) region detector. We call this new detector Maximally Robust Range Regions (MRRR). We apply the new detector to real range data captured by a commercially available laser range camera. Using this data we evaluate the repeatability of the new detector and compare it to some other recently published detectors. The presented detector shows a repeatability which is better or the same as the best of the other detectors. The MRRR detector also offers additional data on the detected regions. The additional data could be crucial in applications such as registration or recognition.

Publisher
p. 8
Series
LiTH-ISY-R, ISSN 1400-3902 ; 2961
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-57332 (URN)LiTH-ISY-R-2961 (ISRN)
Available from: 2010-06-16 Created: 2010-06-16 Last updated: 2018-01-12
Viksten, F. (2010). Object Pose Estimation using Variants of Patch-Duplet and SIFT Descriptors.
Open this publication in new window or tab >>Object Pose Estimation using Variants of Patch-Duplet and SIFT Descriptors
2010 (English)Report (Other academic)
Abstract [en]

Recent years have seen a lot of work on local descriptors. In all published comparisons or evaluations, the now quite well-known SIFT-descriptor has been one of the top performers. For the application of object pose estimation, one comparison showed a local descriptor, called the Patch-duplet, of equal or better performance than SIFT. This paper examines different properties of those two descriptors by constructing and evaluating hybrids of them. We also extend upon the object pose estimation experiments of the original Patch-duplet paper. All tests use real images. We also show what impact camera calibration and image rectification has on an application such as object pose estimation. A new feature based on the Patch-duplet descriptor and the DoG detector emerges as the feature of choice under illuminiation changes in a real world application.

Publisher
p. 15
Series
LiTH-ISY-R, ISSN 1400-3902 ; 2950
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-57331 (URN)LiTH-ISY-R-2950 (ISRN)
Note
This is an extension of work found in http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-56268Available from: 2010-06-16 Created: 2010-06-16 Last updated: 2018-01-12
Viksten, F., Forssén, P.-E., Johansson, B. & Moe, A. (2009). Comparison of Local Image Descriptors for Full 6 Degree-of-Freedom Pose Estimation. In: IEEE ICRA, 2009: 1050-4729. Paper presented at Robotics and Automation, 2009. ICRA '09. IEEE International Conference on (pp. 2779-2786). Kobe: IEEE Robotics and Automation Society
Open this publication in new window or tab >>Comparison of Local Image Descriptors for Full 6 Degree-of-Freedom Pose Estimation
2009 (English)In: IEEE ICRA, 2009: 1050-4729, Kobe: IEEE Robotics and Automation Society , 2009, p. 2779-2786Conference paper, Published paper (Refereed)
Abstract [en]

Recent years have seen advances in the estimation of full 6 degree-of-freedom object pose from a single 2D image. These advances have often been presented as a result of, or together with, a new local image descriptor. This paper examines how the performance for such a system varies with choice of local descriptor. This is done by comparing the performance of a full 6 degree-of-freedom pose estimation system for fourteen types of local descriptors. The evaluation is done on a database with photos of complex objects with simple and complex backgrounds and varying lighting conditions. From the experiments we can conclude that duplet features, that use pairs of interest points, improve pose estimation accuracy, and that affine covariant features do not work well in current pose estimation frameworks. The data sets and their ground truth is available on the web to allow future comparison with novel algorithms.

Place, publisher, year, edition, pages
Kobe: IEEE Robotics and Automation Society, 2009
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-44894 (URN)10.1109/ROBOT.2009.5152360 (DOI)000276080400185 ()78158 (Local ID)9781424427888 (ISBN)78158 (Archive number)78158 (OAI)
Conference
Robotics and Automation, 2009. ICRA '09. IEEE International Conference on
Available from: 2009-10-10 Created: 2009-10-10 Last updated: 2015-12-10
Viksten, F. (2009). Object Pose Estimation using Patch-Duplet/SIFT Hybrids. In: Hideo SAITO (Ed.), Proceedings of the 11th IAPR Conference on Machine Vision Applications. Paper presented at Machine Vision Applications (pp. 134-137). Tokyo, Japan
Open this publication in new window or tab >>Object Pose Estimation using Patch-Duplet/SIFT Hybrids
2009 (English)In: Proceedings of the 11th IAPR Conference on Machine Vision Applications / [ed] Hideo SAITO, Tokyo, Japan, 2009, p. 134-137Conference paper, Published paper (Refereed)
Abstract [en]

Recent years have seen a lot of work on local descriptors. In all published comparisons or evaluations, the now quite well-known SIFT-descriptor has been one of the top performers. For the application of object pose estimation, one comparison showed a local descriptor, called the Patch-Duplet, of equal or better performance than SIFT. This paper examines different properties of those two descriptors by forming hybrids between them and extending the object pose tests of the original Patch-Duplet paper. All tests use real images.

Place, publisher, year, edition, pages
Tokyo, Japan: , 2009
Keywords
bin-picking, vision, local features
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-56268 (URN)978-4-901122-09-2 (ISBN)
Conference
Machine Vision Applications
Available from: 2010-05-06 Created: 2010-05-06 Last updated: 2010-05-06
Viksten, F., Nordberg, K. & Kalms, M. (2008). Point-of-Interest Detection for Range Data. In: International Conference on Pattern Recognition (ICPR): . Paper presented at International Conference on Pattern Recognition (ICPR), December 8-11, Tampa, Florida, USA (pp. 1-4). IEEE
Open this publication in new window or tab >>Point-of-Interest Detection for Range Data
2008 (English)In: International Conference on Pattern Recognition (ICPR), IEEE , 2008, p. 1-4Conference paper, Published paper (Refereed)
Abstract [en]

Point-of-interest detection is a way of reducing the amount of data that needs to be processed in a certain application and is widely used in 2D image analysis. In 2D image analysis, point-of-interest detection is usually related to extraction of local descriptors for object recognition, classification, registration or pose estimation. In analysis of range data however, some local descriptors have been published in the last decade or so, but most of them do not mention any kind of point-of-interest detection. We here show how to use an extended Harris detector on range data and discuss variants of the Harris measure. All described variants of the Harris detector for 3D should also be usable in medical image analysis, but we focus on the range data case. We do present a performance evaluation of the described variants of the Harris detector on range data.

Place, publisher, year, edition, pages
IEEE, 2008
Series
Pattern Recognition, ISSN 1051-4651
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-44928 (URN)10.1109/ICPR.2008.4761179 (DOI)78311 (Local ID)978-1-4244-2175-6 (ISBN)978-1-4244-2174-9 (ISBN)78311 (Archive number)78311 (OAI)
Conference
International Conference on Pattern Recognition (ICPR), December 8-11, Tampa, Florida, USA
Available from: 2009-10-10 Created: 2009-10-10 Last updated: 2018-01-12
Viksten, F. & Nordberg, K. (2007). A Geometry-Based Local Descriptor for Range Data. In: Proceedings of the 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications: Rome, Italy. Paper presented at Digital Image Computing: Techniques and Applications (DICTA), 3-5 December, Adelaide, Australia (pp. 210-217). ACM
Open this publication in new window or tab >>A Geometry-Based Local Descriptor for Range Data
2007 (English)In: Proceedings of the 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications: Rome, Italy, ACM , 2007, p. 210-217Conference paper, Published paper (Refereed)
Abstract [en]

We present a novel local descriptor for range data that can describe one or more planes or lines in a local region. It is possible to recover the geometry of the described local region and extract the size, position and orientation of each local plane or line-like structure from the descriptor. This gives the descriptor a property that other popular local descriptors for range data, such as spin images or point signatures, does not have. The estimation of the descriptor is dependant on estimation of surface normals but does not depend on the specific normal estimation method used. It is shown that is possible to extract how many planar surface regions the descriptor represents and that this could be used as a point-of-interest detector.

Place, publisher, year, edition, pages
ACM, 2007
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-21714 (URN)10.1109/DICTA.2007.4426798 (DOI)0-7695-3067-2 (ISBN)
Conference
Digital Image Computing: Techniques and Applications (DICTA), 3-5 December, Adelaide, Australia
Available from: 2009-10-25 Created: 2009-10-05 Last updated: 2010-05-06
Organisations

Search in DiVA

Show all publications