Computer Vision

Course description


  • The aims of computer vision, the origins of computer vision, and related fields.
  • Computer vision trends and application domains.

Image formation

  • Basic image properties.
  • Perspective projection camera model.
  • Camera calibration, direct linear transform, lens distortion correction.
  • Propagation of light, photometry, photometric lens equation.
  • Cameras and lenses, lighting techniques.
  • Human eye, color perception, reproducing color, color spaces.

Image analysis

  • Image filtering basics, histogramming.
  • Edge detection, corner detection.
  • Hough transform.
  • Connected components analysis.
  • Morphological filtering.
  • Active contour models (snakes).
  • Shape description.
  • Scale space and image pyramids.
  • Geometric image transformations, similarity measures.
  • Image registration, model fitting, RANSAC.

Stereo vision

  • Basic concepts of stereo vision.
  • Stereo matching.
  • Modeling and calibration, epipolar geometry.
  • Active stereo, structured lighting.

Visual motion analysis

  • Motion detection.
  • Time to collision.
  • Optic flow, motion field, velocity field.
  • Visual tracking, Kalman filtering basics.

Course is carried out on study programme

Elektrotehnika 2. stopnja

Objectives and competences

The aims of this course are to understand basic concepts, underlying theory, algorithms, and applications of computer vision, especially in intelligent systems for automation and robotics.

Learning and teaching methods

The lectures provide a theoretical background on particular subjects together with practical examples in Matlab or C.

Practical work is being performed as the part of laboratory exercises, and is accomplished in the form of multiple assignments, acquainting students with computer vision algorithms. Students work in groups, consisting of two or three students, and the results are in the form of Matlab code. After completing each part, students present their results to the assistant.

Intended learning outcomes

After successful completion of the course, the students should be able to:

  • Explain the concept of image formation on a sensor of a digital camera
  • Explain the working  of the widely used computer vision algorithms on a conceptual level
  • Perform camera calibration using the tools that are used for this purpose in the field of computer vision
  • Choose appropriate basic computer vision algorithms for the problem at hand
  • Implement moderately complex computer vision algorithms.
  • Develop moderately difficult solutions for machine vision problems, which are able to work in controlled environments

Reference nosilca

  1. MUHOVIČ, Jon Natanael, MANDELJC, Rok, BOVCON, Borja, KRISTAN, Matej, PERŠ, Janez. Obstacle tracking for unmanned surface vessels using 3-D point cloud. IEEE journal of oceanic engineering. [Print ed.]. 2019, vol. , str. 1-13, ilustr. ISSN 0364-9059., DOI: 10.1109/JOE.2019.2909507. [COBISS.SI-ID 12642388]
  2. KOPOREC, Gregor, VUČKOVIĆ, Goran, MILIĆ, Radoje, PERŠ, Janez. Quantitative contact-less estimation of energy expenditure from video and 3D imagery. Sensors. Aug. 2018, iss. 8, 4235, str. 1-32, ilustr. ISSN 1424-8220., DOI: 10.3390/s18082435. [COBISS.SI-ID 12120148]
  3. KRISTAN, Matej, SULIĆ KENK, Vildana, KOVAČIČ, Stanislav, PERŠ, Janez. Fast image-based obstacle detection from unmanned surface vehicles. IEEE transactions on cybernetics, ISSN 2168-2267, Mar. 2016, vol. 46, no. 3, pp. 641-654.
  4. MANDELJC, Rok, KOVAČIČ, Stanislav, KRISTAN, Matej, PERŠ, Janez. Tracking by identification using computer vision and radio. Sensors, ISSN 1424-8220, Jan. 2013, vol. 13, no. 1, pp. 241-273.
  5. KRISTAN, Matej, KOVAČIČ, Stanislav, LEONARDIS, Aleš, PERŠ, Janez. A two-stage dynamic model for visual tracking. IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics, ISSN 1083-4419, Dec. 2010, vol. 40, no. 6, str. 1505-1520.
  6. PERŠ, Janez, SULIĆ, Vildana, KRISTAN, Matej, PERŠE, Matej, POLANEC, Klemen, KOVAČIČ, Stanislav. Histograms of optical flow for efficient representation of body motion. Pattern recognition letters, ISSN 0167-8655, Aug. 2010, vol. 31, no. 11, str. 1369-137
  7. PERŠE, Matej, KRISTAN, Matej, KOVAČIČ, Stanislav, VUČKOVIĆ, Goran, PERŠ, Janez. A trajectory-based analysis of coordinated team activity in a basketball game. Computer vision and image understanding, ISSN 1077-3142, May 2009, vol. 113, no. 5, str. 612-621.

Study materials

  1. D. Forsyth, J. Ponce, Compuer vision, a modern approach, 2nd ed., Pearson 2012.
  2. E. Trucco, A. Verri, Introductory techniques for 3-D computer vision, Prentice Hall, 1998.
  3. Prosojnice iz predavanj (lecture slides), navodila za vaje (lab assignment instructions).

Bodi na tekočem

Univerza v Ljubljani, Fakulteta za elektrotehniko, Tržaška cesta 25, 1000 Ljubljana

E: T:  01 4768 411