Course details

Computer Vision (in English)

POVa Acad. year 2020/2021 Winter semester 5 credits

Current academic year

Principles and methods of computer vision, methods and principles of image acquiring, preprocessing methods (statistical processing), filtering, pattern recognition, integral transformations - Fourier transform, image morphology, classification problems, automatic classification, D methods of computer vision, open problems of computer vision.

Guarantor

Zemčík Pavel, prof. Dr. Ing., dr. h. c. (DCGM)

Course coordinator

Hradiš Michal, Ing., Ph.D. (DCGM)

Language of instruction

English

Completion

Examination (written)

Time span

  • 26 hrs lectures
  • 26 hrs projects

Assessment points

  • 51 pts final exam (26 pts written part, 25 pts test part)
  • 9 pts mid-term test (3 pts written part, 6 pts test part)
  • 40 pts projects

Department

Department of Computer Graphics and Multimedia (UPGM)

Lecturer

Beran Vítězslav, doc. Ing., Ph.D. (DCGM)
Čadík Martin, doc. Ing., Ph.D. (DCGM)
Hradiš Michal, Ing., Ph.D. (DCGM)
Juránek Roman, Ing., Ph.D. (DCGM)
Najman Pavel, Ing. (DCGM)
Šolony Marek, Ing., Ph.D. (DCGM)
Španěl Michal, Ing., Ph.D. (DCGM)
Zemčík Pavel, prof. Dr. Ing., dr. h. c. (DCGM)

Instructor

Bartl Vojtěch, Ing. (DCGM)
Behúň Kamil, Ing. (DCGM)
Hradiš Michal, Ing., Ph.D. (DCGM)
Juránek Roman, Ing., Ph.D. (DCGM)
Sochor Jakub, Ing., Ph.D.
Špaňhel Jakub, Ing. (DCGM)

Subject specific learning outcomes and competences

The students will get acquainted with the principles and methods of computer vision. They will learn in more detail selected methods and algorithms of vision and image acquiring. They will also get acquainted with the possibilities of the scanned data processing. Finally, they will learn how to apply the gathered knowledge practically.
The students will improve their teamwork skills, mathematics, and exploitation of the "C", C++, and other languages.

Learning objectives

To get acquainted with the principles and methods of computer vision. To learn in more detail selected methods and algorithms of vision and image acquiring. To get acquainted with the possibilities of the scanned data processing. To learn how to apply the gathered knowledge practically.

Why is the course taught

The goal of the course eduation is to invoke interest among students about the principles, tasks, and methods of computer vision. The scope of the course cannot reach the broad area of computer vision but brings at least "bits"of it and shows also results and direction of research at FIT.

Study literature

  • Šonka, M., Hlaváč, V., Boyle, R.: Image processing, Analysis, and Machine Vision, THOMSON 2013, ISBN: 978-9386858146
  • Bass, M.: Handbook of Optics, McGraw-Hill, New York, USA, 1995, ISBN 0-07-047740-X
  • Hlaváč, V., Šonka, M.: Počítačové vidění, Grada, 1993, ISBN 80-85424-67-3
  • Šonka, M., Hlaváč, V., Boyle, R.: Image processing, Analysis, and Machine Vision, THOMSON 2013, ISBN-13: 978-9386858146
  • IEEE Multimedia, IEEE, USA - série časopisů - různé články
  • Forsyth, D.A., Ponce, J.: Computer Vision: A Modern Approach, Prentical Hall 2011, ISBN: 978-0136085928

Fundamental literature

  • Horn, B.K.P.: Robot Vision, McGraw-Hill, 1988, ISBN 0-07-030349-5
  • Hlaváč, V., Šonka, M.: Počítačové vidění, Grada, 1993, ISBN 80-85424-67-3 
  • Russ, J.C.: The IMAGE PROCESSING Handbook, CRC Press, 1995, ISBN 0-8493-2532-3
  • Bass, M.: Handbook of Optics, McGraw-Hill, New York, USA, 1995, ISBN 0-07-047740-X

Syllabus of lectures

  1. Introduction, motivation and applications (Zemčík 24.9. slides, slajdy, highlights)
  2. Basic principles of machine learning with teacher - AdaBoost  (Zemčík 1.10. slajdy-cz, slides-en)
  3. Object Detection - Trees, Random Forests (Juránek, 8.10. slajdy-en)
  4. Hough Transform, RHT, RANSAC, Time Sequence Processing (Hradiš, 15.10. slajdy1,  slajdy2, slajdy2-en)
  5. Clustering, statistical methods (Španěl 22.10. slajdy)
  6. Segmentation, colour analysis, histogram analysis (Španěl 29.10. slajdy1, slajdy2)
  7. Analysis and Feature Extraction from Images (Čadík 5.11. slajdy)
  8. Convolutional Neural Networks and Automatic Image Tagging (Hradiš, 12.11. slajdy, video)
  9. Test, Invariant Image Regions (Beran, 19.11. slajdy)
  10. Image Registration (Čadík, 26.11., slajdy)
  11. 3D Computer Vision - Stereo (3.12. Najman, slajdy)
  12. 3D Computer Vision -SLAM (10.12. Šolony, slajdy)
  13. Acceleration of Processing in Computer Vision (Zemčík, 17.12., slajdy)

    NOTE: The topics and dates are just FYI, not guaranteed,  and will be continuously updated.

Syllabus - others, projects and individual work of students

  1. Homeworks (4-5 runs) at the beginning of semester
  2. Individually assigned project for the whole duration of the course.

Progress assessment

Homeworks, Mid-term test, individual project.

Course inclusion in study plans

Back to top