Course detail

Machine Vision

FSI-VSV-AAcad. year: 2019/2020

The course is aimed at a digital photography fundamentals and processing of digital images within computer vision systems. The course focus at the specifics of the computer vision in terms of lighting and capturing of scenes.

Language of instruction

English

Number of ECTS credits

5

Mode of study

Not applicable.

Guarantor

prof. RNDr. Ing. Jiří Šťastný, CSc.

Department

Institute of Automation and Computer Science (ÚAI)

Offered to foreign students

The home faculty only

Learning outcomes of the course unit

Understanding of basic principles of digital image capturing and processing. Ability to analysis real world problems, to select appropriate hardware for this problem, and to design and implement adequate software.

Prerequisites

Expected to have basic knowledge of algorithms, programming, and of fundamental concepts in mathematics and physics.

Co-requisites

Not applicable.

Planned learning activities and teaching methods

The course is taught through lectures explaining the basic principles and theory of the discipline. Exercises are focused on practical topics presented in lectures.

Assesment methods and criteria linked to learning outcomes

In order to be awarded the course-unit credit, students must prove 100 % active participation in laboratory exercises. The exam is oral where student compiles two main themes which were presented during the lectures.

Course curriculum

Not applicable.

Work placements

Not applicable.

Aims

The goal of the course is understanding of the principles of digital image capturing and processing by students, within the context of industrial and scientific applications.

Specification of controlled education, way of implementation and compensation for absences

Attendance at lectures is recommended, attendance at seminars is obligatory and checked. Absences can be compensated for by attending a seminar with another group in the same week, or at the end of semester within a special seminar.

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

A Practical Guide to Machine Vision Lighting. Automated Test and Automated Measurement Systems - National Instruments [online]. National Instruments, 2019, 30. ledna 2017 [cit. 2019-02-19]. Dostupné z: http://www.ni.com/white-paper/6901/en/
BATCHELOR, Bruce G. Machine vision handbook: with 1295 figures and 117 tables [online]. 1. London: Springer, [2012] [cit. 2019-02-19]. ISBN 978-1-84996-169-1. Dostupné z: https://link.springer.com/referencework/10.1007%2F978-1-84996-169-1
MCMANAMOM, Paul. Field Guide to Lidar. 1. Bellingham, Washington 98227-0010 USA: SPIE, 2015. ISBN 9781628416541.
SZELISKI, Richard. Computer Vision: Algorithms and Applications [online]. 1. London: Springer, 2010 [cit. 2019-02-19]. Texts in computer science. ISBN 978-1-84882-935-0. Dostupné z: https://www.springer.com/gp/book/9781848829343

Recommended reading

HAVEL, Otto. Strojové vidění I: Principy a charakteristiky. Automa. Automa – časopis pro automatizační techniku, s. r. o., 2008, 14(1), 42-45. ISSN 1210-9592.
HAVEL, Otto. Strojové vidění II: Úlohy, nástroje a algoritmy. Automa. Automa – časopis pro automatizační techniku, s. r. o., 2008, 14(2), 54-56. ISSN 1210-9592.
HAVEL, Otto. Strojové vidění III: Kamery a jejich části. Automa. Automa – časopis pro automatizační techniku, s. r. o., 2008, 14(3), 42-44. ISSN 1210-9592.
HAVEL, Otto. Strojové vidění IV: Osvětlovače. Automa. Automa – časopis pro automatizační techniku, s. r. o., 2008, 14(4), 47-49. ISSN 1210-9592.

Classification of course in study plans

  • Programme M2I-A Master's

    branch M-AIŘ , 2 year of study, winter semester, compulsory

  • Programme M2I-Z Master's

    branch M-STI , 1 year of study, winter semester, recommended course

Type of course unit

 

Lecture

26 hod., optionally

Teacher / Lecturer

doc. Ing. Pavel Škrabánek, Ph.D.

Syllabus

1.Basic principles of digital imaging
2. Sensors for digital imaging (area-scan camers)
3. Lens and their properties
4. Lighting techniques for machine vision
5. Filters and their application in computer vision systems
6. Line-scan cameras
7. Digital image representation, digital image enhancement
8. Image filtering, edge detection, feature extraction
9. Segmentation
10. Object recognition
11. Object classification
12. Object tracking
13. Lidar

Laboratory exercise

26 hod., compulsory

Teacher / Lecturer

doc. Ing. Pavel Škrabánek, Ph.D.

Syllabus

1. Introduction to MATLAB – computer vision toolbox.
2.Industrial cameras and their configuration.
3. Selection, installation and setting of lenses, lens defects.
4. Installation and manipulation with lighting. Impact of lighting on displaying of interest areas.
5. Impact of lighting on displaying of interest areas
6. Selection and implementation of filters. Impact of filters on displaying of interest areas.
7. Image enhancement using software tools.
8. Design and implementation of computer vision systems for a given task.
9 .Design and implementation of computer vision systems for a given task.
10. Design and implementation of computer vision systems for a given task.
11. Work with Lidar.
12. Individual project.
13. Individual project.