|
Instructors: Ehsan Yaghoubi
Event type:
Lecture
Displayed in timetable as:
CV 1 - VL
Hours per week:
2
Language of instruction:
English
Min. | Max. participants:
- | 60
Comments/contents:
The field of Computer vision deals with developing algorithms that interpret and modify images.
This lecture requires some pre-knowledge in image processing (basics of histograms, digital filters, etc.), ideally obtained in of the Bachelor lecture "Einführung in die Bildverarbeitung" (introduction to image processing) at our department, but also other image processing courses should provide the required knowledge.
This lecture will put a stronger focus on mid- and high level methods of computer vision such as segmentation and classification.
If you do not have pre-knowledge in IP and still would like to attend the lecture, we provide content for self-study. You should plan for 2-3 weeks of self-study before the semester starts. Login to our Moodle page for more information about which pre-knowledge is necessary and how to obtain it:
Course name: Computer Vision 1 - WiSe 2022/2023
enrollment key: CV1-2223
(if the course is not available yet, try again in a few days)
In particular, the lecture will cover the following topics:
- Machine-learning-based computer vision
- advanced topics of digital filters
- line and circle detection (Hough transform)
- segmentation
- features and interest points, feature-based object recognition
- classification of objects and scenes (e.g. deep learning for computer vision)
Learning objectives:
Knowledge of computer vision methods with a focus on mid and high level methods.
Didactic concept:
Depending on the pandemic situation, the lecture will be held either in presence or videos will be provided via Moodle.
Literature:
The primary literature will be:
R.C. Gonzalez, R.E. Woods: Digital Image Processing (4th edition), Prentice-Hall 2017
Several other relevant computer vision books:
R. Klette: Concise Computer Vision: An Introduction into Theory and Algorithms, Springer 2014
R. Szeliski, Computer Vision: Algorithms and Applications, Springer, 2011
(szeliski.org/Book)
D.A. Forsyth, J. Ponce: Computer Vision, A Modern Approach (2nd edition), Prentice-Hall 2012
Recommended machine learning books:
Deep Learning, MIT Press, Ian Goodfellow and Yoshua Bengio and Aaron Courville, 2016 (https://www.deeplearningbook.org)
Probabilistic Machine Learning: An Introduction by K. P. Murphy. MIT Press, March 2022 (https://probml.github.io/pml-book/book1.html)
Additional literature will be announced during the lecture.
Additional examination information:
There will be a written exam at the end of the term.
|
