A configurable CAD-based object recognition system for varying resolution 3D-sensors

Jari M. Ahola; Tapio Heikkilä; Jukka Koskinen; Tuomas Seppälä; Tarmo Tamminen

doi:10.1109/MESA.2016.7587121

A configurable CAD-based object recognition system for varying resolution 3D-sensors

Jari M. Ahola, Tapio Heikkilä, Jukka Koskinen, Tuomas Seppälä, Tarmo Tamminen

Profin Oy

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

1 Citation (Scopus)

Abstract

This paper presents a configurable CAD-based object recognition system for varying resolution 3D sensors such as Time-Of-Flight (ToF) cameras and laser scanners. The object recognition system is used for recognizing and localizing target objects on the basis of the geometric and topological information extracted from STEP-files. The novelty of our system is its configurability, i.e. its ability to adjust the level of detail of the database object models to the properties of the applied sensor system, e.g., resolution, accuracy and signal to noise ratio.

Original language	English
Title of host publication	Proceedings
Publisher	IEEE Institute of Electrical and Electronic Engineers
ISBN (Print)	978-1-5090-6190-7, 978-1-5090-6189-1
DOIs	https://doi.org/10.1109/MESA.2016.7587121
Publication status	Published - 7 Oct 2016
MoE publication type	A4 Article in a conference publication
Event	12th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2016 - Auckland, New Zealand Duration: 29 Aug 2016 → 31 Aug 2016

Conference

Conference	12th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2016
Abbreviated title	MESA 2016
Country/Territory	New Zealand
City	Auckland
Period	29/08/16 → 31/08/16

Keywords

CAD models
configurable
geometric models
object recognition

Access to Document

10.1109/MESA.2016.7587121

Cite this

@inproceedings{498a9af2b35c4f5c9d8c90c1196c4e82,

title = "A configurable CAD-based object recognition system for varying resolution 3D-sensors",

abstract = "This paper presents a configurable CAD-based object recognition system for varying resolution 3D sensors such as Time-Of-Flight (ToF) cameras and laser scanners. The object recognition system is used for recognizing and localizing target objects on the basis of the geometric and topological information extracted from STEP-files. The novelty of our system is its configurability, i.e. its ability to adjust the level of detail of the database object models to the properties of the applied sensor system, e.g., resolution, accuracy and signal to noise ratio.",

keywords = "CAD models, configurable, geometric models, object recognition",

author = "Ahola, {Jari M.} and Tapio Heikkil{\"a} and Jukka Koskinen and Tuomas Sepp{\"a}l{\"a} and Tarmo Tamminen",

note = "HUO: Article number 7587121 CA2: BA2143 CA2: BA214 CA2: BA2142 PGN: 6 p. AU2: Ahola, Jari M. AU2: Heikkil{\"a}, Tapio AU2: Koskinen, Jukka AU2: Sepp{\"a}l{\"a}, Tuomas; 12th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2016, MESA 2016 ; Conference date: 29-08-2016 Through 31-08-2016",

year = "2016",

month = oct,

day = "7",

doi = "10.1109/MESA.2016.7587121",

language = "English",

isbn = "978-1-5090-6190-7",

booktitle = "Proceedings",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

}

Ahola, JM, Heikkilä, T , Koskinen, J , Seppälä, T & Tamminen, T 2016, A configurable CAD-based object recognition system for varying resolution 3D-sensors. in Proceedings., 7587121, IEEE Institute of Electrical and Electronic Engineers, 12th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2016, Auckland, New Zealand, 29/08/16. https://doi.org/10.1109/MESA.2016.7587121

TY - GEN

T1 - A configurable CAD-based object recognition system for varying resolution 3D-sensors

AU - Ahola, Jari M.

AU - Heikkilä, Tapio

AU - Koskinen, Jukka

AU - Seppälä, Tuomas

AU - Tamminen, Tarmo

N1 - HUO: Article number 7587121 CA2: BA2143 CA2: BA214 CA2: BA2142 PGN: 6 p. AU2: Ahola, Jari M. AU2: Heikkilä, Tapio AU2: Koskinen, Jukka AU2: Seppälä, Tuomas

PY - 2016/10/7

Y1 - 2016/10/7

N2 - This paper presents a configurable CAD-based object recognition system for varying resolution 3D sensors such as Time-Of-Flight (ToF) cameras and laser scanners. The object recognition system is used for recognizing and localizing target objects on the basis of the geometric and topological information extracted from STEP-files. The novelty of our system is its configurability, i.e. its ability to adjust the level of detail of the database object models to the properties of the applied sensor system, e.g., resolution, accuracy and signal to noise ratio.

AB - This paper presents a configurable CAD-based object recognition system for varying resolution 3D sensors such as Time-Of-Flight (ToF) cameras and laser scanners. The object recognition system is used for recognizing and localizing target objects on the basis of the geometric and topological information extracted from STEP-files. The novelty of our system is its configurability, i.e. its ability to adjust the level of detail of the database object models to the properties of the applied sensor system, e.g., resolution, accuracy and signal to noise ratio.

KW - CAD models

KW - configurable

KW - geometric models

KW - object recognition

UR - http://www.scopus.com/inward/record.url?scp=84994213308&partnerID=8YFLogxK

U2 - 10.1109/MESA.2016.7587121

DO - 10.1109/MESA.2016.7587121

M3 - Conference article in proceedings

AN - SCOPUS:84994213308

SN - 978-1-5090-6190-7

SN - 978-1-5090-6189-1

BT - Proceedings

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 12th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2016

Y2 - 29 August 2016 through 31 August 2016

ER -

A configurable CAD-based object recognition system for varying resolution 3D-sensors

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this