Computing the Orientation of Hardware Components from Images using Traditional Computer Vision Methods

Antonio Gambale; Emmett Kerr; Dermot Kerr; Sonya Coleman

doi:10.3390/engproc2024065008

Computing the Orientation of Hardware Components from Images using Traditional Computer Vision Methods

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

59 Downloads (Pure)

Abstract

This paper introduces a methodology for precise object orientation determination using Principal Component Analysis, with robust performance under significant noise conditions. It validates the potential to mitigate the challenges associated with Axis-Aligned Bounding Boxes in smart manufacturing environments. The proposed approach paves the way for improved alignment in robotic grasping tasks, positioning it as a computationally efficient alternative to ML methods employing Oriented Bounding Boxes. The methodology demonstrated a maximum angle deviation of 3.5 degrees under severe noise conditions through testing with bolts in orientations of 0 to 180 degrees.

Original language	English
Title of host publication	The 39th International Manufacturing Conference
Subtitle of host publication	Smart Manufacturing: The Next Generation
Publisher	MDPI
Pages	1-2
Number of pages	2
Volume	65
Edition	1
DOIs	https://doi.org/10.3390/engproc2024065008
Publication status	Published online - 1 Mar 2024
Event	The 39th International Manufacturing Conference: Smart Manufacturing - The Next Generation - Ulster University, Magee Campus, Derry/Londonderry, Northern Ireland Duration: 24 Aug 2023 → 25 Aug 2023 https://www.manufacturingcouncil.ie/imc39-2023

Publication series

Name	Engineering Proceedings
Publisher	MDPI

Conference

Conference	The 39th International Manufacturing Conference
Abbreviated title	IMC39 2023
Country/Territory	Northern Ireland
City	Derry/Londonderry
Period	24/08/23 → 25/08/23
Internet address	https://www.manufacturingcouncil.ie/imc39-2023

Bibliographical note

Publisher Copyright:
© 2024 by the authors.

Funding

This research was funded by the Department for the Economy (DfE). The APC was funded by the Department for the Economy (DfE).

Funders
Department for the Economy

Keywords

Manufacturing
Vision
PCA
Machine Learning
vision
manufacturing
machine learning

Access to Document

10.3390/engproc2024065008

IMC-extended-abstract-Antonio-Gambale_EK-D3Final published version, 182 KBLicence: Unspecified

Cite this

Gambale, A., Kerr, E., Kerr, D., & Coleman, S. (2024). Computing the Orientation of Hardware Components from Images using Traditional Computer Vision Methods. In The 39th International Manufacturing Conference: Smart Manufacturing: The Next Generation (1 ed., Vol. 65, pp. 1-2). Article 8 (Engineering Proceedings). MDPI. Advance online publication. https://doi.org/10.3390/engproc2024065008

@inproceedings{1be3d89972db48c08e0d70e7523372c3,

title = "Computing the Orientation of Hardware Components from Images using Traditional Computer Vision Methods",

abstract = "This paper introduces a methodology for precise object orientation determination using Principal Component Analysis, with robust performance under significant noise conditions. It validates the potential to mitigate the challenges associated with Axis-Aligned Bounding Boxes in smart manufacturing environments. The proposed approach paves the way for improved alignment in robotic grasping tasks, positioning it as a computationally efficient alternative to ML methods employing Oriented Bounding Boxes. The methodology demonstrated a maximum angle deviation of 3.5 degrees under severe noise conditions through testing with bolts in orientations of 0 to 180 degrees.",

keywords = "Manufacturing , Vision, PCA, Machine Learning, vision, manufacturing, machine learning",

author = "Antonio Gambale and Emmett Kerr and Dermot Kerr and Sonya Coleman",

note = "Publisher Copyright: {\textcopyright} 2024 by the authors.; The 39th International Manufacturing Conference : Smart Manufacturing - The Next Generation, IMC39 2023 ; Conference date: 24-08-2023 Through 25-08-2023",

year = "2024",

month = mar,

day = "1",

doi = "10.3390/engproc2024065008",

language = "English",

volume = "65",

series = "Engineering Proceedings",

publisher = "MDPI",

pages = "1--2",

booktitle = "The 39th International Manufacturing Conference",

address = "Switzerland",

edition = "1",

url = "https://www.manufacturingcouncil.ie/imc39-2023",

}

Gambale, A , Kerr, E , Kerr, D & Coleman, S 2024, Computing the Orientation of Hardware Components from Images using Traditional Computer Vision Methods. in The 39th International Manufacturing Conference: Smart Manufacturing: The Next Generation . 1 edn, vol. 65, 8, Engineering Proceedings, MDPI, pp. 1-2, The 39th International Manufacturing Conference, Derry/Londonderry, Northern Ireland, 24/08/23. https://doi.org/10.3390/engproc2024065008

Computing the Orientation of Hardware Components from Images using Traditional Computer Vision Methods. / Gambale, Antonio ; Kerr, Emmett ; Kerr, Dermot et al.
The 39th International Manufacturing Conference: Smart Manufacturing: The Next Generation . Vol. 65 1. ed. MDPI, 2024. p. 1-2 8 (Engineering Proceedings).

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

TY - GEN

T1 - Computing the Orientation of Hardware Components from Images using Traditional Computer Vision Methods

AU - Gambale, Antonio

AU - Kerr, Emmett

AU - Kerr, Dermot

AU - Coleman, Sonya

PY - 2024/3/1

Y1 - 2024/3/1

N2 - This paper introduces a methodology for precise object orientation determination using Principal Component Analysis, with robust performance under significant noise conditions. It validates the potential to mitigate the challenges associated with Axis-Aligned Bounding Boxes in smart manufacturing environments. The proposed approach paves the way for improved alignment in robotic grasping tasks, positioning it as a computationally efficient alternative to ML methods employing Oriented Bounding Boxes. The methodology demonstrated a maximum angle deviation of 3.5 degrees under severe noise conditions through testing with bolts in orientations of 0 to 180 degrees.

AB - This paper introduces a methodology for precise object orientation determination using Principal Component Analysis, with robust performance under significant noise conditions. It validates the potential to mitigate the challenges associated with Axis-Aligned Bounding Boxes in smart manufacturing environments. The proposed approach paves the way for improved alignment in robotic grasping tasks, positioning it as a computationally efficient alternative to ML methods employing Oriented Bounding Boxes. The methodology demonstrated a maximum angle deviation of 3.5 degrees under severe noise conditions through testing with bolts in orientations of 0 to 180 degrees.

KW - Manufacturing

KW - Vision

KW - PCA

KW - Machine Learning

KW - vision

KW - manufacturing

KW - machine learning

UR - https://www.scopus.com/pages/publications/85196543628

U2 - 10.3390/engproc2024065008

DO - 10.3390/engproc2024065008

M3 - Conference contribution

VL - 65

T3 - Engineering Proceedings

SP - 1

EP - 2

BT - The 39th International Manufacturing Conference

PB - MDPI

T2 - The 39th International Manufacturing Conference

Y2 - 24 August 2023 through 25 August 2023

ER -

Computing the Orientation of Hardware Components from Images using Traditional Computer Vision Methods

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this