Fast visual part inspection for bin picking

Nikolaos Rofalis; Anders Sig Olesen; Michael Linde Jakobsen; Volker Kruger

doi:10.1109/IST.2016.7738261

Fast visual part inspection for bin picking

Nikolaos Rofalis
, Anders Sig Olesen
, Michael Linde Jakobsen
, Volker Kruger

Aalborg University

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

432 Downloads (Orbit)

Abstract

In this paper we present a novel 3D sensing approach for industrial bin-picking applications that is low-cost, fast and precise. The system uses a simple laser-line emitter. While a robot arm moves the object through the laser light, a synchronized camera captures the laser line image on the object. A full point cloud as well as an edge point cloud suitable for subsequent pose estimation is generated by the developed system. The aim of this work is to deliver an accurate point cloud based on which an object pose can be generated to support a manufacturing robot to deliver an object with high precision. The experimental evaluation of our system shows robust and accurate scanning results.

Original language	English
Title of host publication	Proceedings of 2016 IEEE International Conference on Imaging Systems and Techniques
Publisher	IEEE
Publication date	2016
Pages	412-17
ISBN (Print)	978-1-5090-1817-8
DOIs	https://doi.org/10.1109/IST.2016.7738261
Publication status	Published - 2016
Event	2016 IEEE International Conference on Imaging Systems and Techniques - Chania, Crete Island, Greece Duration: 4 Oct 2016 → 6 Oct 2016

Conference

Conference	2016 IEEE International Conference on Imaging Systems and Techniques
Country/Territory	Greece
City	Chania, Crete Island
Period	04/10/2016 → 06/10/2016

Access to Document

10.1109/IST.2016.7738261

NRofalis Fast visual part inspection for bin picking IEEE2016Accepted author manuscript, 3.26 MB

OpenUrl availability

Full text

Cite this

@inproceedings{1ec311253c364b668b111d2633dfd1e1,

title = "Fast visual part inspection for bin picking",

abstract = "In this paper we present a novel 3D sensing approach for industrial bin-picking applications that is low-cost, fast and precise. The system uses a simple laser-line emitter. While a robot arm moves the object through the laser light, a synchronized camera captures the laser line image on the object. A full point cloud as well as an edge point cloud suitable for subsequent pose estimation is generated by the developed system. The aim of this work is to deliver an accurate point cloud based on which an object pose can be generated to support a manufacturing robot to deliver an object with high precision. The experimental evaluation of our system shows robust and accurate scanning results.",

author = "Nikolaos Rofalis and Olesen, \{Anders Sig\} and Jakobsen, \{Michael Linde\} and Volker Kruger",

year = "2016",

doi = "10.1109/IST.2016.7738261",

language = "English",

isbn = "978-1-5090-1817-8",

pages = "412--17",

booktitle = "Proceedings of 2016 IEEE International Conference on Imaging Systems and Techniques",

publisher = "IEEE",

address = "United States",

note = "2016 IEEE International Conference on Imaging Systems and Techniques, IST 2016 ; Conference date: 04-10-2016 Through 06-10-2016",

}

TY - GEN

T1 - Fast visual part inspection for bin picking

AU - Rofalis, Nikolaos

AU - Olesen, Anders Sig

AU - Jakobsen, Michael Linde

AU - Kruger, Volker

PY - 2016

Y1 - 2016

N2 - In this paper we present a novel 3D sensing approach for industrial bin-picking applications that is low-cost, fast and precise. The system uses a simple laser-line emitter. While a robot arm moves the object through the laser light, a synchronized camera captures the laser line image on the object. A full point cloud as well as an edge point cloud suitable for subsequent pose estimation is generated by the developed system. The aim of this work is to deliver an accurate point cloud based on which an object pose can be generated to support a manufacturing robot to deliver an object with high precision. The experimental evaluation of our system shows robust and accurate scanning results.

AB - In this paper we present a novel 3D sensing approach for industrial bin-picking applications that is low-cost, fast and precise. The system uses a simple laser-line emitter. While a robot arm moves the object through the laser light, a synchronized camera captures the laser line image on the object. A full point cloud as well as an edge point cloud suitable for subsequent pose estimation is generated by the developed system. The aim of this work is to deliver an accurate point cloud based on which an object pose can be generated to support a manufacturing robot to deliver an object with high precision. The experimental evaluation of our system shows robust and accurate scanning results.

U2 - 10.1109/IST.2016.7738261

DO - 10.1109/IST.2016.7738261

M3 - Article in proceedings

SN - 978-1-5090-1817-8

SP - 412

EP - 417

BT - Proceedings of 2016 IEEE International Conference on Imaging Systems and Techniques

PB - IEEE

T2 - 2016 IEEE International Conference on Imaging Systems and Techniques

Y2 - 4 October 2016 through 6 October 2016

ER -

Fast visual part inspection for bin picking

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this