Navigation

13M051KV - Computer Vision

Course specification
Course title Computer Vision
Acronym 13M051KV
Study programme Electrical Engineering and Computing
Module Signals and Systems
Type of study master academic studies
Lecturer (for classes)
Lecturer/Associate (for practice)
    Lecturer/Associate (for OTC)
    ESPB 6.0 Status elective
    Condition Digital image processing (OS4DOS, MS1DOS), Pattern recognition (OS4PO, MS1PO)
    The goal The aim of the course is to familiarize students with the modern directions of computer vision, which have a tremendous trend in the world in the last two decades. Students will be familiar with the basics of image formation, characteristic features properties in the image, stereo-vision problems, recognition of objects in images or video sequences and computer tools that are being used for.
    The outcome After completing the course, students will be able to independently solve problems related to digital image processing, object recognition and tracking in video sequences, and will be familiar with potential applications in surveillance systems, modern systems for people and objects tracking, medicine, television, professional photography, etc.
    Contents
    URL to the subject page http://automatika.etf.bg.edu.rs/sr/13m051kv
    Contents of lectures Basic principles of image formation, Color, Filters and image pyramids, local features, panoramic image stitching, perspective projections, stereo-vision, object recognition in the image, face recognition, image retrieval, etc.
    Contents of exercises Using MATLAB and its specific toolboxes for digital image processing and computer vision to solve various problems related to scientific, research, medical and commercial applications.
    Literature
    1. Computer Vision: Algorithms and Applications, Richard Szeliski, Springer, 2010
    2. Computer Vision: A Modern Approach, David Forsyth and Jean Ponce, Prentice Hall, 2003
    3. Computer Vision, Linda Shapiro, George Stockman, Prentice Hall, 2001
    Number of hours per week during the semester/trimester/year
    Lectures Exercises OTC Study and Research Other classes
    3 0 2
    Methods of teaching 45 classes of theoretical lectures + 15 classes of computer exercises + 15 classes of individual computer work All together 60 hours of independent learning + 30 hours for solving homework problems + 50 hours for preparation of final exam.
    Knowledge score (maximum points 100)
    Pre obligations Points Final exam Points
    Activites during lectures 0 Test paper 0
    Practical lessons 20 Oral examination 30
    Projects
    Colloquia 0
    Seminars 50