HS2023: 31062/61062 Computer Vision

This course covers fundamental topics in computer vision. The course will provide an introduction to image formation, image processing, feature detection, segmentation, multiple view geometry and 3D reconstruction.

Syllabus Material (preliminary -- subject to updates)

Introduction & projection models (also see book: Forsyth & Ponce Ch 1 & 2)
Camera models, image filtering (also see book: Forsyth & Ponce Ch 1 & 2, Ch. 7 & 8)
Edges, deblurring, denoising, numerical methods (also see book: Forsyth & Ponce Ch. 7 & 8)
Photometric stereo & shading (book: Forsyth & Ponce Ch 4 & 5)
Tracking, optical flow (book: Forsyth & Ponce Ch 17)
Interest points detection (book: Grauman & Leibe)
Registration and fitting (book: Forsyth & Ponce Ch 15)
Epipolar geometry & stereo (book: Forsyth & Ponce Ch 10 & 11)
Multiview stereo and structure from motion (book: Forsyth & Ponce Ch 12 & 13)
Bayesian methods in imaging (slides only)
Clustering and segmentation (book: Forsyth & Ponce Ch 14, 15 & 16)

Additional reading:
• Computer Vision : A Modern Approach, David A. Forsyth and Jean Ponce.
• Algorithms and Applications, Rick Szeliski.

Upon successful completion of this class, you will be able to:
1) Understand how cameras capture images of a scene
2) Implement and use: algorithms for image processing such as image filtering and image segmentation;
algorithms for 3D reconstruction (e.g., from stereo systems)
3) Describe the mathematics underpinning each method and know how to adapt it to other scenarios

English

All rights reserved

Kontaktangaben: Dr. Andreas Humm, Universität Freiburg, Departement für Informatik, Bd de Pérolles 90, CH-1700 Freiburg
Tel.: +41 26 300 92 89, andreas.humm@unifr.ch

Unlimited

You can join this course directly.

Unlimited

Username
First Name
Last Name
E-Mail