Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications

Tuomas Seppälä; Janne Saukkoriipi; Taneli Lohi; Samuli Soutukorva; Tapio Heikkilä; Jukka Koskinen

doi:10.1109/MESA55290.2022.10004402

Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications

Tuomas Seppälä, Janne Saukkoriipi, Taneli Lohi, Samuli Soutukorva, Tapio Heikkilä, Jukka Koskinen

BA5602 Intelligent robotics

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

Abstract

This paper presents a feature-based object detection and pose estimation method. In this approach, a user selects geometric features from a CAD model of an object. The selected features are then matched against measured features from the 3D cameras. Software modules were developed for the method and were tested in a robot cell. Based on the results, our approach provides a fast way to configure and program the pose estimation system for new objects. Target applications of the approach are in small series and agile, even one-of-a-kind manufacturing.

Original language	English
Title of host publication	MESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications
Subtitle of host publication	Proceedings
Publisher	IEEE Institute of Electrical and Electronic Engineers
Number of pages	5
ISBN (Electronic)	978-1-6654-5570-1
DOIs	https://doi.org/10.1109/MESA55290.2022.10004402
Publication status	Published - 2022
MoE publication type	A4 Article in a conference publication
Event	18th International Conference on Mechatronic, Embedded Systems and Applications, IEEE/ASME MESA 2022 : Hybrid Event - National Taiwan University of Science and Technology International Building 202, Taipei, Taiwan, Province of China Duration: 28 Nov 2022 → 30 Nov 2022

Conference

Conference	18th International Conference on Mechatronic, Embedded Systems and Applications, IEEE/ASME MESA 2022
Country/Territory	Taiwan, Province of China
City	Taipei
Period	28/11/22 → 30/11/22

Keywords

3D cameras
CAD models
Object detection
Robotics

Access to Document

10.1109/MESA55290.2022.10004402

Cite this

Seppälä, T., Saukkoriipi, J., Lohi, T., Soutukorva, S., Heikkilä, T., & Koskinen, J. (2022). Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications. In MESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications: Proceedings IEEE Institute of Electrical and Electronic Engineers. https://doi.org/10.1109/MESA55290.2022.10004402

@inproceedings{9c9bb16819c0441db5b54a260f20566f,

title = "Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications",

abstract = "This paper presents a feature-based object detection and pose estimation method. In this approach, a user selects geometric features from a CAD model of an object. The selected features are then matched against measured features from the 3D cameras. Software modules were developed for the method and were tested in a robot cell. Based on the results, our approach provides a fast way to configure and program the pose estimation system for new objects. Target applications of the approach are in small series and agile, even one-of-a-kind manufacturing.",

keywords = "3D cameras, CAD models, Object detection, Robotics",

author = "Tuomas Sepp{\"a}l{\"a} and Janne Saukkoriipi and Taneli Lohi and Samuli Soutukorva and Tapio Heikkil{\"a} and Jukka Koskinen",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 18th International Conference on Mechatronic, Embedded Systems and Applications, IEEE/ASME MESA 2022 : Hybrid Event ; Conference date: 28-11-2022 Through 30-11-2022",

year = "2022",

doi = "10.1109/MESA55290.2022.10004402",

language = "English",

booktitle = "MESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications",

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

address = "United States",

}

Seppälä, T , Saukkoriipi, J, Lohi, T, Soutukorva, S, Heikkilä, T & Koskinen, J 2022, Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications. in MESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications: Proceedings. IEEE Institute of Electrical and Electronic Engineers, 18th International Conference on Mechatronic, Embedded Systems and Applications, IEEE/ASME MESA 2022 , Taipei, Taiwan, Province of China, 28/11/22. https://doi.org/10.1109/MESA55290.2022.10004402

Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications. / Seppälä, Tuomas ; Saukkoriipi, Janne; Lohi, Taneli et al.
MESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications: Proceedings. IEEE Institute of Electrical and Electronic Engineers, 2022.

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

TY - GEN

T1 - Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications

AU - Seppälä, Tuomas

AU - Saukkoriipi, Janne

AU - Lohi, Taneli

AU - Soutukorva, Samuli

AU - Heikkilä, Tapio

AU - Koskinen, Jukka

PY - 2022

Y1 - 2022

N2 - This paper presents a feature-based object detection and pose estimation method. In this approach, a user selects geometric features from a CAD model of an object. The selected features are then matched against measured features from the 3D cameras. Software modules were developed for the method and were tested in a robot cell. Based on the results, our approach provides a fast way to configure and program the pose estimation system for new objects. Target applications of the approach are in small series and agile, even one-of-a-kind manufacturing.

AB - This paper presents a feature-based object detection and pose estimation method. In this approach, a user selects geometric features from a CAD model of an object. The selected features are then matched against measured features from the 3D cameras. Software modules were developed for the method and were tested in a robot cell. Based on the results, our approach provides a fast way to configure and program the pose estimation system for new objects. Target applications of the approach are in small series and agile, even one-of-a-kind manufacturing.

KW - 3D cameras

KW - CAD models

KW - Object detection

KW - Robotics

UR - http://www.scopus.com/inward/record.url?scp=85146875585&partnerID=8YFLogxK

U2 - 10.1109/MESA55290.2022.10004402

DO - 10.1109/MESA55290.2022.10004402

M3 - Conference article in proceedings

BT - MESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 18th International Conference on Mechatronic, Embedded Systems and Applications, IEEE/ASME MESA 2022

Y2 - 28 November 2022 through 30 November 2022

ER -

Seppälä T , Saukkoriipi J, Lohi T, Soutukorva S, Heikkilä T , Koskinen J. Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications. In MESA 2022 - 18th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications: Proceedings. IEEE Institute of Electrical and Electronic Engineers. 2022 doi: 10.1109/MESA55290.2022.10004402

Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

CCM: Cognitive Collaborative Manufacturing

Cite this

Feature-Based Object Detection and Pose Estimation Based on 3D Cameras and CAD Models for Industrial Robot Applications

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

CCM: Cognitive Collaborative Manufacturing

Cite this