Skip to main content

Machine VisionLaajuus (5 cr)

Code: TSAR0520

Credits

5 op

Teaching language

  • Finnish

Responsible person

  • Samppa Alanen

Objective

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Qualifications

Fundamentals in field of technology, programming skills

Assessment criteria, satisfactory (1)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Assessment criteria, good (3)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Assessment criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Enrollment

01.11.2024 - 09.01.2025

Timing

13.01.2025 - 18.05.2025

Number of ECTS credits allocated

5 op

Mode of delivery

Face-to-face

Unit

School of Technology

Campus

Lutakko Campus

Teaching languages
  • Finnish
Seats

20 - 35

Degree programmes
  • Bachelor's Degree Programme in Electrical and Automation Engineering
Teachers
  • Samppa Alanen
Groups
  • TSA22SS
    Sähkö- ja automaatiotekniikka (AMK)
  • TSA22SA
    Sähkö- ja automaatiotekniikka (AMK)

Objectives

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Learning materials and recommended literature

Materials in the e-learning environment.

Teaching methods

- independent study
- distance learning
- webinars
- small group learning
- laboratory work
- learning tasks

Exam dates and retake possibilities

The possible date and method of the exam will be announced in the course opening.

Alternative completion methods

The admission procedures are described in the degree rule and the study guide. The teacher of the course will give you more information on possible specific course practices.

Student workload

One credit (1 Cr) corresponds to an average of 27 hours of work.

- lectures 40h
- independent study and assignments 50h
- laboratory work and small group learning 45h
Total 135 h

Further information for students

The evaluation is based on the qualitative evaluation of the exam and exercises/assignments.

Evaluation scale

0-5

Evaluation criteria, satisfactory (1-2)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Evaluation criteria, good (3-4)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Evaluation criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Prerequisites

Fundamentals in field of technology, programming skills

Enrollment

01.11.2024 - 09.01.2025

Timing

13.01.2025 - 18.05.2025

Number of ECTS credits allocated

5 op

Mode of delivery

Face-to-face

Unit

School of Technology

Campus

Lutakko Campus

Teaching languages
  • English
Seats

20 - 35

Degree programmes
  • Bachelor's Degree Programme in Electrical and Automation Engineering
Teachers
  • Samppa Alanen
Groups
  • TAR22S1
    Bachelor's Degree Programme in Automation and Robotics

Objectives

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Learning materials and recommended literature

Materials in the e-learning environment.

Teaching methods

- independent study
- distance learning
- webinars
- small group learning
- laboratory work
- learning tasks

Exam dates and retake possibilities

The possible date and method of the exam will be announced in the course opening.

Alternative completion methods

The admission procedures are described in the degree rule and the study guide. The teacher of the course will give you more information on possible specific course practices.

Student workload

One credit (1 Cr) corresponds to an average of 27 hours of work.

- lectures 40h
- independent study and assignments 50h
- laboratory work and small group learning 45h
Total 135 h

Further information for students

The evaluation is based on the qualitative evaluation of the exam and exercises/assignments.

Evaluation scale

0-5

Evaluation criteria, satisfactory (1-2)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Evaluation criteria, good (3-4)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Evaluation criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Prerequisites

Fundamentals in field of technology, programming skills

Enrollment

01.08.2024 - 22.08.2024

Timing

01.08.2024 - 31.12.2024

Number of ECTS credits allocated

5 op

Virtual portion

3 op

Mode of delivery

40 % Face-to-face, 60 % Online learning

Unit

School of Technology

Campus

Main Campus

Teaching languages
  • Finnish
Degree programmes
  • Bachelor's Degree Programme in Electrical and Automation Engineering
Teachers
  • Samppa Alanen
  • Juho Riekkinen
Groups
  • TSA22KMA
    Sähkö- ja automaatiotekniikka (AMK)
  • TSA22KMS
    Sähkö- ja automaatiotekniikka (AMK)

Objectives

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Learning materials and recommended literature

Materials in the e-learning environment.

Teaching methods

- independent study
- distance learning
- webinars
- small group learning
- laboratory work
- learning tasks

Exam dates and retake possibilities

The possible date and method of the exam will be announced in the course opening.

Alternative completion methods

The admission procedures are described in the degree rule and the study guide. The teacher of the course will give you more information on possible specific course practices.

Student workload

One credit (1 Cr) corresponds to an average of 27 hours of work.

- remote lectures 15h
- independent study and assignments 75h
- laboratory work and small group learning 45h
Total 135 h

Further information for students

The evaluation is based on the qualitative evaluation of the exam and exercises/assignments.

Evaluation scale

0-5

Evaluation criteria, satisfactory (1-2)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Evaluation criteria, good (3-4)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Evaluation criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Prerequisites

Fundamentals in field of technology, programming skills

Timing

07.03.2023 - 31.12.2024

Number of ECTS credits allocated

5 op

Virtual portion

5 op

Mode of delivery

Online learning

Unit

School of Technology

Campus

Main Campus

Teaching languages
  • Finnish
Degree programmes
  • Bachelor's Degree Programme in Electrical and Automation Engineering
Teachers
  • Samppa Alanen
  • Juho Riekkinen
Groups
  • ZJA23SLIKEROK
    Avoin amk, Like, Liiketoiminnallisesti kestävän robotiikan kehittäjä
  • ZJAJ23KLIKEROK
    Liiketoiminnallisesti kestävän robotiikan kehittäjä

Objectives

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Evaluation scale

Pass/Fail

Evaluation criteria, satisfactory (1-2)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Evaluation criteria, good (3-4)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Evaluation criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Prerequisites

Fundamentals in field of technology, programming skills

Enrollment

20.11.2023 - 04.01.2024

Timing

01.01.2024 - 05.05.2024

Number of ECTS credits allocated

5 op

Virtual portion

3 op

Mode of delivery

40 % Face-to-face, 60 % Online learning

Unit

School of Technology

Campus

Main Campus

Teaching languages
  • Finnish
Degree programmes
  • Bachelor's Degree Programme in Electrical and Automation Engineering
Teachers
  • Samppa Alanen
  • Juho Riekkinen
Groups
  • TSA21SA
    Sähkö- ja automaatiotekniikka (AMK)
  • TSA21SB
    Sähkö- ja automaatiotekniikka (AMK)

Objectives

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Learning materials and recommended literature

Materials in the e-learning environment.

Teaching methods

- independent study
- distance learning
- webinars
- small group learning
- laboratory work
- learning tasks

Exam dates and retake possibilities

The possible date and method of the exam will be announced in the course opening.

Alternative completion methods

The admission procedures are described in the degree rule and the study guide. The teacher of the course will give you more information on possible specific course practices.

Student workload

One credit (1 Cr) corresponds to an average of 27 hours of work.

- remote lectures 10h
- independent study and assignments 80h
- laboratory work and small group learning 45h
Total 135 h

Further information for students

The evaluation is based on the qualitative evaluation of the exam and exercises/assignments.

Evaluation scale

0-5

Evaluation criteria, satisfactory (1-2)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Evaluation criteria, good (3-4)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Evaluation criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Prerequisites

Fundamentals in field of technology, programming skills

Enrollment

01.08.2023 - 24.08.2023

Timing

04.09.2023 - 19.12.2023

Number of ECTS credits allocated

5 op

Virtual portion

3 op

Mode of delivery

40 % Face-to-face, 60 % Online learning

Unit

School of Technology

Campus

Main Campus

Teaching languages
  • Finnish
Seats

0 - 25

Degree programmes
  • Bachelor's Degree Programme in Electrical and Automation Engineering
Teachers
  • Samppa Alanen
  • Juho Riekkinen
Groups
  • TSA21KMB
    Sähkö- ja automaatiotekniikka (AMK)
  • TSA21KMA
    Sähkö- ja automaatiotekniikka (AMK)

Objectives

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Learning materials and recommended literature

Materials in the e-learning environment.

Teaching methods

- independent study
- distance learning
- webinars
- small group learning
- laboratory work
- learning tasks

Exam dates and retake possibilities

The possible date and method of the exam will be announced in the course opening.

Alternative completion methods

The admission procedures are described in the degree rule and the study guide. The teacher of the course will give you more information on possible specific course practices.

Student workload

One credit (1 Cr) corresponds to an average of 27 hours of work.

- remote lectures 10h
- independent study and assignments 80h
- laboratory work and small group learning 45h
Total 135 h

Evaluation scale

0-5

Evaluation criteria, satisfactory (1-2)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Evaluation criteria, good (3-4)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Evaluation criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Prerequisites

Fundamentals in field of technology, programming skills

Enrollment

01.11.2022 - 05.01.2023

Timing

09.01.2023 - 30.04.2023

Number of ECTS credits allocated

5 op

Mode of delivery

Face-to-face

Unit

School of Technology

Campus

Main Campus

Teaching languages
  • Finnish
Degree programmes
  • Bachelor's Degree Programme in Electrical and Automation Engineering
Teachers
  • Samppa Alanen
  • Juho Riekkinen
Groups
  • TSA20SA
    Bachelor's Degree Programme in Electrical and Automation Engineering
  • TSA20SB
    Bachelor's Degree Programme in Electrical and Automation Engineering

Objectives

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Evaluation scale

0-5

Evaluation criteria, satisfactory (1-2)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Evaluation criteria, good (3-4)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Evaluation criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Prerequisites

Fundamentals in field of technology, programming skills

Timing

16.03.2022 - 14.08.2022

Number of ECTS credits allocated

5 op

Virtual portion

5 op

Mode of delivery

Online learning

Unit

School of Technology

Campus

Main Campus

Teaching languages
  • Finnish
Degree programmes
  • Bachelor's Degree Programme in Electrical and Automation Engineering
Teachers
  • Juho Riekkinen
Groups
  • ZJA21SLKRK
    Avoin AMK, Liiketoiminnallisesti kestävän robotiikan kehittäjä

Objectives

Main objectives for this course are acquiring knowledge and getting familiar with different types of machine vision systems and solutions (including robotics applications). Studying in this course require fundamentals in field of technology and programming skills. This course enables further studies of the subject in other courses.

EUR-ACE ENGINEERING PRACTICE
Student is familiar and able to use image acquisition, image pre-processing and image analysis functions in machine vision systems with grayscale and color cameras. Student is familiar with hardware component properties (cameras, image processing components, light sources, optics, connections) in machine vision. Student understands functionalities, limits and opportunities in machine vision systems. Student is able to design machine vision system and program machine vision application and algorithms according to end-user requirements. Student is able to design the installation of the machine vision system according to end-user needs (designing optical geometry, choosing camera and lightning options, implementing interface to automation system, designing environmental protection).

Content

Camera and lightning technologies
Optics
Image acquisition
Image analysis
Designing machine vision system
Programming machine vision application and applying machine vision algorithms
Interfaces for external systems

Evaluation scale

Pass/Fail

Evaluation criteria, satisfactory (1-2)

Sufficient (1): Students is partly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and implementation is significantly incomplete.

Satisfactory (2): Student is mainly able to design machine vision system and take into account the requirements of the application. Students is able to design and implement hardware, software and installations for machine vision applications but the design and/or implementation is incomplete.

Evaluation criteria, good (3-4)

Good (3): Student is able to solve machine vision system design and installation issues according to the requirements of the application. Students is able to design and implement machine vision applications in a functional way including component selection, software and installations. Despite functional implementation, selections and/or implementation are not optimal.

Very good (4): Student is able to manage the design and installation challenges of a machine vision system according to the requirements of the application. Students is able to design and implement machine vision applications in a very good way including component selection, software and installations but there are small selection or implementation differences in the solutions compared to the optimal.

Evaluation criteria, excellent (5)

Excellent (5): Student is able to master the design and installation of a machine vision system according to the requirements of the application. Student is able to design and implement challenging machine vision applications in an optimal way including component selection, software and installations.

Prerequisites

Fundamentals in field of technology, programming skills