Computer Vision

Instructor: Shohreh Kasaei Certificate: Official (bilingual)
Term: Summer 2025 Prerequisite: Deep Learning
Schedule: Tuesday 14:00-17:00 Online Class: Online Class

General Objective

"Computer Vision" refers to a set of methods and algorithms that enable computers to understand the content of images and videos. In this course, students will learn about data acquisition and processing methods, scene understanding, object classification, and 3D scene reconstruction. They will acquire fundamental theoretical knowledge and become familiar with modern applications in the field.

Topics

  • Course introduction, basic definitions, and applications
  • Review of signal and image processing
  • 3D geometry
  • Cameras and projection
  • 3D reconstruction
  • Multi-view reconstruction
  • Keypoint extraction
  • Keypoint matching
  • Robust model fitting
  • Data grouping (clustering, segmentation, and classification)
  • Deep learning in computer vision

Assessment

  • Final Exam: 14 points
  • Assignments and Project: 6 points

References

  1. KTH Lecture Notes on Geometric Computing, Stefan Carlsson, http://www.nada.kth.se/~stefanc/gc_lec_notes.pdf
  2. Computer Vision: Algorithms and Applications, Richard Szeliski, Springer; 1st Edition (Oct. 1, 2010), ISBN-10: 1848829345, ISBN-13: 978-1848829343.
  3. An Invitation to 3-D Vision, Yi Ma, Stefano Soatto, Jana Kosecka, & Shankar Sastry, Springer (November 14, 2003), ISBN-10: 0387008934, ISBN-13: 978-0387008936.
  4. Computer Vision – A Modern Approach, David A. Forsyth & Jean Ponce, Prentice Hall; US ed Edition (August 24, 2002), ISBN-10: 0130851981, ISBN-13: 978-0130851987.