Machine vision

Subject description

This course delves into the modelling of visual systems, covering the physical, mathematical, biological, and computational fundamentals. It incorporates selected mathematical tools and algorithms for the analysis of visual information, highlighting topics from linear algebra, stochastic systems, and information theory. 

The course further explores algorithms for the detection and tracking of objects and events, motion analysis, and the assessment of activities based on visual information. Special emphasis is placed on multi-sensor visual systems and biologically motivated architectures for visual sensing, including visual sensor networks and embedded visual systems. 

The application of machine vision in industrial contexts, such as visual inspection and measurement, is examined. Additionally, the course addresses the use of machine vision in advanced visual surveillance systems, biometric systems, and robotics, showcasing its impact across various fields. 

The role of machine vision in sports for analyzing individual and team activities is discussed, alongside its integration into advanced user interfaces. This comprehensive approach offers insights into the evolving landscape of machine vision and its applications, fostering a deeper understanding of how visual systems can enhance interaction and interpretation of the visual world. 

The subject is taught in programs

Objectives and competences

Getting familiar with engineering, mathematical, physical, algorithmical and biological foundations of visual perception. Preparation for scientific research and development in the field of artificial visual perception systems.

Teaching and learning methods

The course will be comprised of lectures and  project assignments.

Lectures will be given by the lecturer and the co-lecturer.  

Project assigment will be divided into self-contained parts, providing the framework for individual study of selected methods and algorithms. Each of the assignment parts will require written report and  presentation/defense in front of other students.

Important part of the study are discussions in the class. Each candidate also presents a theoretical topic related to the project assignment.

Expected study results

After completing the course, students will be able to:

independently and critically evaluate state of the art in the field of of artificial visual perception systems.

Perfom doctoral grade research in this field by developing and analyzing novel algorithms and methods.

 Understand the importance of objective, quantitative evaluation of developed methods and have the skills to perform such an evaluation.

Basic sources and literature

  1. Forsyth, David A., in Jean Ponce. Computer Vision: A Modern Approach. 2nd ed., Pearson, cop. 2012. Boston [etc.]. ISBN 978-0-13-608592-8, 0-13-608592-X. COBISS.SI-ID: 10640724. Dostopno v knjižnici UL FE.

  2. Sonka, Milan, Václav Hlaváč, in Roger Boyle, 1954-. Image Processing, Analysis and Machine Vision. 3rd ed., International Student Ed. Cengage Learning, cop. 2008, Stamford [etc.]. ISBN 0-495-24438-4, 978-0-495-24438-7. COBISS.SI-ID: 6473044. Na voljo v knjižnici FE. 

  3. Szeliski, Richard. Computer Vision: Algorithms and Applications. Springer, cop. 2011. London [etc.]. ISBN 978-1-84882-934-3, 1-84882-934-5, 1-84882-935-3. Dostopno na SpringerLink za uporabnike z dostopom do univerzitetne računalniške mreže ali preko storitve Oddaljeni dostop do informacijskih virov UL. COBISS.SI-ID: 9030996. 

  4.  Pomembnejši znanstveni članki iz tematike (Classic scientific papers on the topic) 

Stay up to date

University of Ljubljana, Faculty of Electrical Engineering Tržaška cesta 25, 1000 Ljubljana

E: T:  01 4768 411