Course detail

Computer Vision

FIT-POVAcad. year: 2013/2014

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.

Language of instruction

Czech

Number of ECTS credits

Mode of study

Not applicable.

Guarantor

prof. Dr. Ing. Pavel Zemčík, dr. h. c.

Department

Department of Computer Graphics and Multimedia (UPGM)

Learning outcomes of the course unit

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" language.

Prerequisites

There are no prerequisites

Co-requisites

Not applicable.

Planned learning activities and teaching methods

The course uses teaching methods in form of Lecture - 2 teaching hours per week, Projects - 1 teaching hour per week.

Assesment methods and criteria linked to learning outcomes

Study evaluation is based on marks obtained for specified items. Minimimum number of marks to pass is 50.

Course curriculum

    Syllabus of lectures:
    1. Introduction, basic principles, pre-processing and normalization
    2. Segmentation, color analysis, histogram analysis, clustering
    3. Texture features analysis and acquiring
    4. Clusters, statistical methods
    5. Curves, curve parametrization
    6. Geometrical shapes extraction, Hough transform, RHT
    7. Pattern recognition (statistical, structural)
    8. Classifiers (AdaBoost, neural nets...), automatic clustering
    9. Detection and parametrization of objects in images
    10. Geometrical transformations, RANSAC applications
    11. Motion analysis, object tracking
    12. 3D methods of computer vision, registration, reconstruction
    13. Conclusion, open problems of computer vision

    Syllabus - others, projects and individual work of students:
    1. Homeworks (5 runs) at the beginning of semester
    2. Individually assigned project for the whole duration of the course.

Work placements

Not applicable.

Aims

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.

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

Homeworks, Mid-term test, individual project.

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic 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

Recommended reading

Žára, J., kol.: Počítačová grafika-principy a algoritmy, Grada, 1992, ISBN 80-85623-00-5 Forsyth, D. A., Ponce, J.: Computer Vision A Modern Approach, Prentice Hall, New Jersey, USA, 2003, ISBN 0-13-085198-1

Classification of course in study plans

  • Programme IT-MSC-2 Master's

    branch MBS , 0 year of study, winter semester, elective
    branch MIN , 0 year of study, winter semester, compulsory-optional
    branch MIS , 2 year of study, winter semester, elective
    branch MMI , 0 year of study, winter semester, elective
    branch MMM , 0 year of study, winter semester, elective
    branch MPV , 2 year of study, winter semester, compulsory-optional
    branch MBI , 0 year of study, winter semester, elective
    branch MGM , 0 year of study, winter semester, compulsory-optional
    branch MSK , 0 year of study, winter semester, elective

Type of course unit

 

Lecture

26 hod., optionally

Teacher / Lecturer

prof. Dr. Ing. Pavel Zemčík, dr. h. c.

Syllabus

  1. Introduction, basic principles, pre-processing and normalization
  2. Segmentation, colour analysis, histogram analysis, clustering
  3. Texture features analysis and acquiring
  4. Clusters, statistical methods
  5. Curves, curve parametrization
  6. Geometrical shapes extraction, Hough transform, RHT
  7. Pattern recognition (statistical, structural)
  8. Classifiers (AdaBoost, neural nets...), automatic clustering
  9. Detection and parametrization of objects in images
  10. Geometrical transformations, RANSAC applications
  11. Motion analysis, object tracking
  12. 3D methods of computer vision, registration, reconstruction
  13. Conclusion, open problems of computer vision

Project

26 hod., optionally

Teacher / Lecturer

prof. Dr. Ing. Pavel Zemčík, dr. h. c.