Three-Dimensional Computer Vision

Course Description

The course studies basics of threedimensional computer vision. In particular, we consider pasive stereoscopic reconstruction, reconstruction withh structured light and specifics of reconstruction with LIDAR sensors.

Learning Outcomes

  1. Explain advantages of reconstruction techniques based on pasive stereoscopy.
  2. Explain advantages of reconstruction based on active illumination.
  3. Explain advantages of reconstruction based on LIDAR sensors.

Forms of Teaching

Lectures

13 lectures of two hours each.

Laboratory

One exercise in each half of the semester.

Week by Week Schedule

  1. Image formation, Feature detection and matching, Feature-based alignment
  2. Feature detection and matching, Feature-based alignment, Structure from motion
  3. Stereo
  4. Stereo
  5. Stereo
  6. 3D reconstruction
  7. 3D reconstruction
  8. Midterm exam
  9. 3D reconstruction
  10. 3D reconstruction
  11. Image formation, 3D reconstruction
  12. 3D reconstruction
  13. 3D reconstruction
  14. 3D reconstruction
  15. Final exam

Study Programmes

Literature

Richard Szeliski (2010.), Computer Vision, Springer
Ian Goodfellow, Yoshua Bengio, Aaron Courville (2016.), Deep Learning, MIT Press

For students

General

ID 223691
  Winter semester
5 ECTS
L1 English Level
L1 e-Learning
30 Lectures
8 Laboratory exercises

Grading System

89 Excellent
76 Very Good
63 Good
50 Acceptable