Jan Dirk Wegner: Katalogdaten im Herbstsemester 2021

NameHerr Prof. Dr. Jan Dirk Wegner
(Professor Universität Zürich (UZH))
Adresse
I. f. Geodäsie u. Photogrammetrie
ETH Zürich, HIL D 44.2
Stefano-Franscini-Platz 5
8093 Zürich
SWITZERLAND
Telefon+41 44 633 68 08
E-Mailjan.wegner@geod.baug.ethz.ch
DepartementBau, Umwelt und Geomatik
BeziehungDozent

NummerTitelECTSUmfangDozierende
103-0274-AALImage Processing
Belegung ist NUR erlaubt für MSc Studierende, die diese Lerneinheit als Auflagenfach verfügt haben.

Alle andere Studierenden (u.a. auch Mobilitätsstudierende, Doktorierende) können diese Lerneinheit NICHT belegen.
3 KP6RJ. D. Wegner
KurzbeschreibungIntroduction to basic concepts and methods of digital image processing.
LernzielUnderstanding core methods and algorithms in image processing and computer vision and the underlying signal processing foundations.
Applying image processing algorithms to relevant problems in photogrammetry and remote sensing.
Inhalt- Properties of digital images
- Sampling, quantisation and signal processing
- Colour spaces and transformations
- Geometric image transformations
- Image morphology
- Discrete convolution
- Image filtering
- Texture descriptors
- 2D Fourier transform and the Fourier domain
- Pattern recognition: corner and edge extraction
- Image segmentation
Literatur- Gonzales, Woods, 2008: Digital Image Processing, Pearson Prentice Hall
- Jähne, 2012: Digitale Bildverarbeitung und Bildgewinnung, Springer
- Sonka, Hlavac, Boyle 2007: Image Processing, Analysis, and Machine Vision, Springer
- Burger, Burge, 2013: Digitale Bildverarbeitung: Eine algorithmische Einführung mit Java, Springer


We suggest the following textbooks for further reading:

Rafael C. Gonzalez, Richard E. Woods
Digital Image Processing
Prentice Hall International, 2008
ISBN: 013168728X

Rafael C. Gonzalez, Steven L. Eddins, Richard E. Woods:
Digital Image Processing Using MATLAB
Prentice Hall, 2003
ISBN: 0130085197
851-0650-00LAI4Good Belegung eingeschränkt - Details anzeigen 3 KP2GJ. D. Wegner
KurzbeschreibungThe AI4Good course is a hackathon turned into a full course. At the beginning, stakeholders active in the development sector will describe several problems that could be solved with a machine learning approach. Students will spend the semester on designing, implementing, and testing suitable solutions using machine learning. Progress will be discussed with all course members.
LernzielGiven a specific problem in global development, students shall learn to self-responsibly design, implement and experimentally evaluate a suitable solution. Students will also learn to critically evaluate their ideas and solutions together with all course members in a broader context that go beyond mere technical solutions, but touch on ethics, local culture etc., too.
InhaltThe AI4Good course is a hackathon turned into a full course. At the beginning of the course, stakeholders (e.g., NGOs) active in the development sector will describe several problems that could be solved with a machine learning approach. Organizers of the course will make sure that only those problems are selected that are suitable for a machine learning approach and where sufficient amounts of data (and labels) are available. Students will organize themselves into small groups of 3-5 students, where each group works on solving a specific problem. Students will spend the semester on designing, implementing, and testing suitable solutions using machine learning. Every two weeks, each group will present ideas and progress during a short presentation followed by a discussion with all course members. At the end of the course, students will present their final results and submit source code. In addition, they will describe the developed method in form of a scientific paper of 8 pages. Grading will depend on the source code, the paper, and active participation in class.

Note: The course AI4Good is not related to Hack4Good, which is a students' initiative organized by the Analytics Club at ETH. For more information about Hack4Good check out the website: https://analytics-club.org/wordpress/hack4good/.
Voraussetzungen / BesonderesStudents with a strong background in machine learning and excellent programming skills (preferably in Python)