Instructors: Prof. Dr. Simone Frintrop; Dr. Mikko Lauri; Ehsan Yaghoubi
Event type:
Seminar
Displayed in timetable as:
CV2 - Sem
Hours per week:
2
Credits:
3,0
Language of instruction:
English
Min. | Max. participants:
- | 60
Comments/contents:
Seminar including practical programming exercises associated with the lecture. Topics are closely related to the lecture content, and may include, e.g., visual attention modeling, saliency computation, and object discovery.
Learning objectives:
Getting hands-on experience with implementing methods in computer vision.
Critically analysing and evaluating scientific literature and giving research presentations.
Didactic concept:
Course language is English.
One part of the course will consist of practical programming exercise, the second part of a seminar.
Programming exercises are done in Python. Libraries such as skimage or PyTorch may be applied. Exercises of CV1 course provide sufficient programming pre-knowledge. Knowledge of the libraries mentioned is helpful. Substantial self-study is required in case of no Python knowledge. A software project related to computer vision will be completed by the participants and submitted.
The seminar part consists of reading and reporting on relevant esearch literature on recent active topics in computer vision.
The course requires pre-knowledge of basic computer vision concepts, such as convolution and digital filters, as for example obtained from the "Computer Vision I/Image Processing lecture IP1". If no such course was taken, it is necessary to obtain the required knowledge in self-study.
Depending on the situation, the course will be given in presence or online with Zoom meetings.
Literature:
Will be announced during the seminar.
|