Object recognition and pose estimation based on combined use of projection histograms and surface fitting

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

In this paper we present a configurable object recognition and locating system for 3D point cloud sensors. The objects are recognized based on cylindrical projection histograms and after the object is recognized, the initial pose of the object is computed based on the eigenvectors of the modelled and measured 3D point clusters. The optimal 6 degree of freedom pose is estimated by fitting the CAD-model surfaces to the measured 3D-points, where the model surfaces and 3D points are correlated based on the modelled and measured eigenvectors. The novelty of our system is the combination of reliable histogram based object recognition and accurate CAD-based pose estimation in the object recognition system with configurability options according to application requirements and point cloud properties.

Original languageEnglish
Title of host publication13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications
PublisherAmerican Society of Mechanical Engineers ASME
Number of pages7
Volume9
ISBN (Electronic)978-0-7918-5823-3
DOIs
Publication statusPublished - 1 Jan 2017
MoE publication typeA4 Article in a conference publication
Event13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications - Cleveland, United States
Duration: 6 Aug 20179 Aug 2017
Conference number: 13

Publication series

NameASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
PublisherAmerican Society of Mechanical Engineers ASME
Volume9

Conference

Conference13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications
Abbreviated titleIDETC/CIE 2017
CountryUnited States
CityCleveland
Period6/08/179/08/17

Fingerprint

Surface Fitting
Pose Estimation
Object recognition
Object Recognition
Histogram
Point Cloud
Projection
Eigenvalues and eigenfunctions
Eigenvector
Computer aided design
Degree of freedom
Sensor
Requirements
Sensors
Model
Object

Keywords

  • object recognition
  • CAD models
  • geometric models

Cite this

Ahola, J., & Heikkilä, T. (2017). Object recognition and pose estimation based on combined use of projection histograms and surface fitting. In 13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications (Vol. 9). [DETC2017-67315] American Society of Mechanical Engineers ASME. ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Vol.. 9 https://doi.org/10.1115/DETC2017-67315
Ahola, Jari ; Heikkilä, Tapio. / Object recognition and pose estimation based on combined use of projection histograms and surface fitting. 13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications. Vol. 9 American Society of Mechanical Engineers ASME, 2017. (ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Vol. 9).
@inproceedings{3048a4b8952d4eb19d5ed546f47c0bfe,
title = "Object recognition and pose estimation based on combined use of projection histograms and surface fitting",
abstract = "In this paper we present a configurable object recognition and locating system for 3D point cloud sensors. The objects are recognized based on cylindrical projection histograms and after the object is recognized, the initial pose of the object is computed based on the eigenvectors of the modelled and measured 3D point clusters. The optimal 6 degree of freedom pose is estimated by fitting the CAD-model surfaces to the measured 3D-points, where the model surfaces and 3D points are correlated based on the modelled and measured eigenvectors. The novelty of our system is the combination of reliable histogram based object recognition and accurate CAD-based pose estimation in the object recognition system with configurability options according to application requirements and point cloud properties.",
keywords = "object recognition, CAD models, geometric models",
author = "Jari Ahola and Tapio Heikkil{\"a}",
note = "Project code: 111677",
year = "2017",
month = "1",
day = "1",
doi = "10.1115/DETC2017-67315",
language = "English",
volume = "9",
series = "ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference",
publisher = "American Society of Mechanical Engineers ASME",
booktitle = "13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications",
address = "United States",

}

Ahola, J & Heikkilä, T 2017, Object recognition and pose estimation based on combined use of projection histograms and surface fitting. in 13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications. vol. 9, DETC2017-67315, American Society of Mechanical Engineers ASME, ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, vol. 9, 13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications, Cleveland, United States, 6/08/17. https://doi.org/10.1115/DETC2017-67315

Object recognition and pose estimation based on combined use of projection histograms and surface fitting. / Ahola, Jari; Heikkilä, Tapio.

13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications. Vol. 9 American Society of Mechanical Engineers ASME, 2017. DETC2017-67315 (ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Vol. 9).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Object recognition and pose estimation based on combined use of projection histograms and surface fitting

AU - Ahola, Jari

AU - Heikkilä, Tapio

N1 - Project code: 111677

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In this paper we present a configurable object recognition and locating system for 3D point cloud sensors. The objects are recognized based on cylindrical projection histograms and after the object is recognized, the initial pose of the object is computed based on the eigenvectors of the modelled and measured 3D point clusters. The optimal 6 degree of freedom pose is estimated by fitting the CAD-model surfaces to the measured 3D-points, where the model surfaces and 3D points are correlated based on the modelled and measured eigenvectors. The novelty of our system is the combination of reliable histogram based object recognition and accurate CAD-based pose estimation in the object recognition system with configurability options according to application requirements and point cloud properties.

AB - In this paper we present a configurable object recognition and locating system for 3D point cloud sensors. The objects are recognized based on cylindrical projection histograms and after the object is recognized, the initial pose of the object is computed based on the eigenvectors of the modelled and measured 3D point clusters. The optimal 6 degree of freedom pose is estimated by fitting the CAD-model surfaces to the measured 3D-points, where the model surfaces and 3D points are correlated based on the modelled and measured eigenvectors. The novelty of our system is the combination of reliable histogram based object recognition and accurate CAD-based pose estimation in the object recognition system with configurability options according to application requirements and point cloud properties.

KW - object recognition

KW - CAD models

KW - geometric models

UR - http://www.scopus.com/inward/record.url?scp=85034980770&partnerID=8YFLogxK

U2 - 10.1115/DETC2017-67315

DO - 10.1115/DETC2017-67315

M3 - Conference article in proceedings

VL - 9

T3 - ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference

BT - 13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications

PB - American Society of Mechanical Engineers ASME

ER -

Ahola J, Heikkilä T. Object recognition and pose estimation based on combined use of projection histograms and surface fitting. In 13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications. Vol. 9. American Society of Mechanical Engineers ASME. 2017. DETC2017-67315. (ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Vol. 9). https://doi.org/10.1115/DETC2017-67315