Real-time Computer Vision in Industrial Automation
(2021)Department of Automatic Control
- Abstract
- The field of computer vision is growing larger and larger every day, fuelled by lower cost, higher computational power, and more sophisticated cameras. This trend, in tandem with the ongoing rise of Industry 4.0, provides new and exciting opportunities to innovate in areas where this technology has not yet been widely adopted or explored.
This thesis aims to investigate the ways in which real-time computer vision can be utilized in the field of industrial automation, and the benefits and challenges that it brings. Firstly, a literature survey was carried out, exploring previous research to identify trends and applications used in the field today. Secondly, a range of experiments were evaluated to give an overview of the parameters that... (More) - The field of computer vision is growing larger and larger every day, fuelled by lower cost, higher computational power, and more sophisticated cameras. This trend, in tandem with the ongoing rise of Industry 4.0, provides new and exciting opportunities to innovate in areas where this technology has not yet been widely adopted or explored.
This thesis aims to investigate the ways in which real-time computer vision can be utilized in the field of industrial automation, and the benefits and challenges that it brings. Firstly, a literature survey was carried out, exploring previous research to identify trends and applications used in the field today. Secondly, a range of experiments were evaluated to give an overview of the parameters that affect the performance of a vision-based system. Finally, a prototype for a pick-and-place application was implemented to compare a vision-based system with a traditional system.
The results show great potential for the adaptation of real-time computer vision in the field of industrial automation. There is a promising opportunity for computer vision to be able to take a larger role in the field and replace many of the more traditional systems, based on its similar performance and unique characteristics. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9064532
- author
- Cedergren, Joakim and Berglund, Jonathan
- supervisor
- organization
- year
- 2021
- type
- H3 - Professional qualifications (4 Years - )
- subject
- report number
- TFRT-6130
- other publication id
- 0280-5316
- language
- English
- id
- 9064532
- date added to LUP
- 2021-09-01 15:49:09
- date last changed
- 2021-09-01 15:49:09
@misc{9064532,
abstract = {{The field of computer vision is growing larger and larger every day, fuelled by lower cost, higher computational power, and more sophisticated cameras. This trend, in tandem with the ongoing rise of Industry 4.0, provides new and exciting opportunities to innovate in areas where this technology has not yet been widely adopted or explored.
This thesis aims to investigate the ways in which real-time computer vision can be utilized in the field of industrial automation, and the benefits and challenges that it brings. Firstly, a literature survey was carried out, exploring previous research to identify trends and applications used in the field today. Secondly, a range of experiments were evaluated to give an overview of the parameters that affect the performance of a vision-based system. Finally, a prototype for a pick-and-place application was implemented to compare a vision-based system with a traditional system.
The results show great potential for the adaptation of real-time computer vision in the field of industrial automation. There is a promising opportunity for computer vision to be able to take a larger role in the field and replace many of the more traditional systems, based on its similar performance and unique characteristics.}},
author = {{Cedergren, Joakim and Berglund, Jonathan}},
language = {{eng}},
note = {{Student Paper}},
title = {{Real-time Computer Vision in Industrial Automation}},
year = {{2021}},
}