Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching

Thomas B. Moeslund, Jakob Kirkegaard

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

382 Downloads (Pure)

Abstract

In this work we address the general bin-picking problem where 3D data is available. We apply Harmonic Shape Contexts (HSC) features since these are invariant to translation, scale, and 3D rotation. Each object is divided into a number of sub-models each represented by a number of HSC features. These are compared with HSC features extracted in the current data using a graph-based scheme. Results show that the approach is somewhat sensitive to noise, but works in presence of occlusion.
Original languageEnglish
Title of host publication18th. International Conference on Pattern Recognition 2006. ICPR 2006
Number of pages4
Volume2
Publication date2006
Pages581-584
Publication statusPublished - 2006
Event18th International Conference on Pattern Recognition, 2006. ICPR 2006 - Hong Kong, China
Duration: 20 Aug 200624 Aug 2006
Conference number: 18

Conference

Conference18th International Conference on Pattern Recognition, 2006. ICPR 2006
Number18
CountryChina
CityHong Kong
Period20/08/200624/08/2006

Fingerprint

Bins

Cite this

Moeslund, T. B., & Kirkegaard, J. (2006). Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching. In 18th. International Conference on Pattern Recognition 2006. ICPR 2006 (Vol. 2, pp. 581-584)
Moeslund, Thomas B. ; Kirkegaard, Jakob. / Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching. 18th. International Conference on Pattern Recognition 2006. ICPR 2006. Vol. 2 2006. pp. 581-584
@inproceedings{5de17060a54a11dbb8eb000ea68e967b,
title = "Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching",
abstract = "In this work we address the general bin-picking problem where 3D data is available. We apply Harmonic Shape Contexts (HSC) features since these are invariant to translation, scale, and 3D rotation. Each object is divided into a number of sub-models each represented by a number of HSC features. These are compared with HSC features extracted in the current data using a graph-based scheme. Results show that the approach is somewhat sensitive to noise, but works in presence of occlusion.",
author = "Moeslund, {Thomas B.} and Jakob Kirkegaard",
year = "2006",
language = "English",
volume = "2",
pages = "581--584",
booktitle = "18th. International Conference on Pattern Recognition 2006. ICPR 2006",

}

Moeslund, TB & Kirkegaard, J 2006, Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching. in 18th. International Conference on Pattern Recognition 2006. ICPR 2006. vol. 2, pp. 581-584, 18th International Conference on Pattern Recognition, 2006. ICPR 2006, Hong Kong, China, 20/08/2006.

Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching. / Moeslund, Thomas B.; Kirkegaard, Jakob.

18th. International Conference on Pattern Recognition 2006. ICPR 2006. Vol. 2 2006. p. 581-584.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching

AU - Moeslund, Thomas B.

AU - Kirkegaard, Jakob

PY - 2006

Y1 - 2006

N2 - In this work we address the general bin-picking problem where 3D data is available. We apply Harmonic Shape Contexts (HSC) features since these are invariant to translation, scale, and 3D rotation. Each object is divided into a number of sub-models each represented by a number of HSC features. These are compared with HSC features extracted in the current data using a graph-based scheme. Results show that the approach is somewhat sensitive to noise, but works in presence of occlusion.

AB - In this work we address the general bin-picking problem where 3D data is available. We apply Harmonic Shape Contexts (HSC) features since these are invariant to translation, scale, and 3D rotation. Each object is divided into a number of sub-models each represented by a number of HSC features. These are compared with HSC features extracted in the current data using a graph-based scheme. Results show that the approach is somewhat sensitive to noise, but works in presence of occlusion.

M3 - Article in proceeding

VL - 2

SP - 581

EP - 584

BT - 18th. International Conference on Pattern Recognition 2006. ICPR 2006

ER -

Moeslund TB, Kirkegaard J. Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching. In 18th. International Conference on Pattern Recognition 2006. ICPR 2006. Vol. 2. 2006. p. 581-584