Course detail
Computer Vision
FEKT-MPOVAcad. year: 2019/2020
The Computer Vision course addresses methods for acquisition and digital processing of an image data. The main parts of the course are technical equipments, algorithms and methods for image processing.
Supervisor
Learning outcomes of the course unit
Graduates of the course are acquainted with basic physical principles and technical equipments used in computer vision. The graduate is able to design and implement algorithms and methods of image data processing, object segmentation, pattern recognition, dynamic scene analysis, optical 3D measurement, OCR, etc. In laboratory exercises students solve problems representing the most common applications of computer vision.
Prerequisites
The knowledge on the level of the Bachelor's degree is required in the Computer Vision course. Moreover, knowledge and skills equivalent to BZSV course are required.
Co-requisites
Not applicable.
Recommended optional programme components
Not applicable.
Recommended or required reading
Sonka M., Hlavac V., Boyle R.: Image Processing, Analysis and Machine Vision. Thomson 2008. ISBN 978-0-495-08252-1. (EN)
Russ J.C.: The Image Processing Handbook. CRC Press 1995. ISBN 0-8493-2516-1. (EN)
Hlaváč V., Šonka M.: Počítačové vidění. Grada 1992. ISBN 80-85424-67-3. (CS)
Planned learning activities and teaching methods
Teaching methods include lectures and computer exercises. Course is taking advantage of e-learning (Midas) system. Students have to write a single project/assignment during the course.
Assesment methods and criteria linked to learning outcomes
In the subject Computer vision are evaluated compulsory laboratory exercises (40 points) and final written (49 points) and oral (11 points) exam. The condition for admission to the exam is the credit from the exercises, ie attendance at all exercises and gain at least 50% points. For successful completion of the course it is necessary to obtain at least half the number of points from the exercises and the written part of the exam. The oral part of the exam is non-compulsory.
Language of instruction
Czech
Work placements
Not applicable.
Course curriculum
1. Introduction and motivation.
2. Basic physics concepts.
3. Optics in computer vision.
4. Electronics in computer vision.
5. Segmentation.
6. Detection of geometrical primitives.
7. Objects detection and plane measuring.
8. Objects description.
9. Classification and automatic sorting.
10. Optical character recognition.
11. Motion analysis.
12. Optical 3D measuring.
13. Traffic applications.
Aims
An absolvent is able to describe algorithms for image processing and to implement them into an superordinate system of computer vision.
Specification of controlled education, way of implementation and compensation for absences
The content and forms of instruction in the evaluated course are specified by a regulation issued by the lecturer responsible for the course and updated for every academic year.
Type of course unit
Lecture
39 hours, optionally
Teacher / Lecturer