FPF:UINA357 Computer Vision - Course Information

UINA357 Computer Vision

Extent and Intensity

2/2/0. 6 credit(s). Type of Completion: zk (examination).

Teacher(s)

doc. Ing. Petr Čermák, Ph.D. (lecturer)
doc. Ing. Petr Čermák, Ph.D. (seminar tutor)

Guaranteed by

Ing. Jiří Blahuta, Ph.D.
Institute of Computer Science – Faculty of Philosophy and Science in Opava

Course Enrolment Limitations

The course is also offered to the students of the fields other than those the course is directly associated with.

fields of study / plans the course is directly associated with

• Computer Science and Technology (programme FPF, N1801 Inf)
• Computer Science (programme FPF, CompSci-np)

Course objectives

Computer Vision is a course which is closely related with robotics and image analysis. The course is focused on successful analysis of input image followed by desired reaction. During the course are discussed practical applications of the mostly used computer vision algorithms in C#, C++ and also in MATLAB with Image Processing Toolbox.

Learning outcomes

After completing the course, the student will know how to preprocess an image, what a histogram is, why a filter is used, when to use segmentation, analyze an image over time, use a discrete Kalman filter. How to analyze and track movement with a camera or multiple cameras, use optical flow. Know what is roi area.

Syllabus

• 1. Image pre-processing. Practical implementation of the following algorithms:
  a. conversion color 24bit RGB image into 8bit grayscale (C#), different approaches
  b. convolution filters demos, e.g. edge detection, edge enhancing, blur, sharpening, relief and other filters
  2. Segmentation and feature recognition. Practical implementation:
  a. Quadtree decomposition (C#)
  b. Global thresholding (C#)
  c. Line finding (C#)
  3. Reverse stereoprojection, camera model, two cameras case, absolute and relative calibration and reconstruction
  4. Analysis of time-variant images by Discrete Kalman Filter
  5. Objects tracking in images from moving camera
  6. Motion detection, image substraction methods
  7. Environment model estimation
  8. Optical flow. Practical implementation of the following algorithms:
  a. Lucas-Kanade algorithm to motion detection (MATLAB)
  9. Interest point detection, SURF/SIFT method comparison (C++)

Literature

required literature
• Haralick Shapiro. Computer vision. New York. info
• SOJKA, E. Zpracování digitálního obrazu. 2000. ISBN 80-7078-746-5. info
• HARALICK, R. M. , SHAPIRO, L. G. Computer and Robot Vision. New York, 1992. info

recommended literature
• Čermák, P., Blahuta, J., Martinu, J. Počítačové vidění. Opava, 2013. URL info
• SZELISKI, Richard. Computer Vision: Algorithms and Applications. Berlin, 2010. info
• DOUGHERTY, G. Digital Image Processing for Medical Applications. Oxford, 2009. ISBN 978-0521860857. info
• ŽÁRA, Jiří, SOCHOR, Jiří, FELKEL, Petr, BENEŠ, Bedřich. Moderní počítačová grafika. Brno, 2005. ISBN 978-80-2510-454-5. info
• SCHLESINGER, M.I., HLAVÁČ, V. Deset přednášek z teorie statistického a strukturního rozpoznávání. Praha, 1999. info
• ŠONKA, M., HLAVÁČ, V., BOYLE, R. Image Processing, Analysis and Machine Vision. Boston, 1998. info
• PRATT, W. K. Digital Image Processing, Second Edition. New York, 1991. info

Teaching methods

Interactive lecture
Lecture with a video analysis

Assessment methods

Exam

Language of instruction

English

Further comments (probably available only in Czech)

The course can also be completed outside the examination period.

Teacher's information

* 75% attendance in the lecture and exercises, active participation
* written test in the extent of the given literature and the content of seminars - success rate 50% of 30 points
* implementation of selected methods of computer vision on selected robot, success rate 50% of 30 points from programming and 10 points from documentation
* 40 points exam, sucess rate 50%

• Enrolment Statistics (Summer 2025, recent)
  
• Permalink: https://is.slu.cz/course/fpf/summer2025/UINA357