infCV3D-01a: 3D Computer Vision (infCV3D-01a) (080010)- Dozent/in
- Prof. Dr.-Ing. Kevin Köser
- Angaben
- Vorlesung, 4 SWS, ECTS-Studium, ECTS-Credits: 8
Unterrichtssprache Englisch
Zeit und Ort: Di 10:15 - 11:45, LMS8 - R.EG.010 (26); Mi 8:15 - 9:45, LMS8 - R.EG.009 (24)
vom 9.4.2023 bis zum 9.7.2023
- Voraussetzungen / Organisatorisches
- Basic mathematical knowledge from Bachelor courses in linear algebra, 3-D geometry and solving of linear equations. Basic knowledge in image processing, like the Bachelor lecture InfEinfBV (Introduction to Image Processing) is requested. You are requested to register at both OLAT and StudiDB starting April 4th, 2022.
1. Please register for this course at StudiDB https://studidb.informatik.uni-kiel.de:8484/studierende/login
2. Please register for course materials at the OLAT course https://lms.uni-kiel.de
Due to large thematic overlap, students cannot combine the ECTS points of this module with points of the module "Image-based 3D Scene Reconstruction" of previous semesters.
- Inhalt
- Using the two different perspectives of our eyes, the human brain is able to obtain a 3D perception of the surrounding scene, and our eyes are probably our most important sense to act in a complex world. Even when moving with only one eye open we can avoid obstacles, estimate distances and understand the 3D layout of our environment, capabilities that are becoming increasingly important also for self-driving cars, service robots or in industry.
This lecture will introduce the basic principles of 3D computer vision, which are nowadays also used in augmented reality, smartphones, for terrain mapping such as for the deep ocean floor, or to create models for 3D printing, archaeology or computer games.
In order to treat machine vision in a principled way, the mathematical pinhole camera model is introduced, and students will learn the representations of points, lines and other entities in images and in space using projective geometry. Afterwards, multiple view relations will be discussed and how camera motion and scene geometry can be inferred from common observations in images, called correspondences. This involves linear algebra, optimization and robust estimation, since we have to deal with mismatches and outliers when automatically finding correspondences. Finally, we will look into how to integrate the different concepts into a complete approach for 3D vision from images, how to obtain dense surface models and see current applications and open problems in 3D vision.
The lecture will be complemented by programming exercises in Octave/Matlab.
- Empfohlene Literatur
- Literature:
Szeliski, Rick: Computer Vision: Algorithms and Applications. Springer 12010. Elektronische Version: http://szeliski.org/Book/
Hartley, Zissermann: Multiple View Geometry, Cambridge 2003.
Schreer: Stereoanalyse und Bildsynthese, Springer 2004
- Zusätzliche Informationen
- Erwartete Teilnehmerzahl: 25
www: https://www.geomar.de/en/omv-teaching
- Zugeordnete Lehrveranstaltungen
- UE: Exercise: 3D Computer Vision (080100)
-
Dozentinnen/Dozenten: Tim Michels, M.Sc., M.Sc. Patricia Schöntag, Jakob Nazarenus, M.Sc.
Zeit und Ort: Di 14:15 - 15:45, LMS8 - R.EG.009 (24)
|
|
