Learning outcome

Expected learning outcomes:

Having completed the course, the student should have gained knowledge, skills and general competences related to selected topics in visual information processing.

Knowledge:The student is in the forefront of knowledge of core issues from different sub-areas of visual information processing research including visual information segmentation, visual information coding, visual information analyses, multiview and multimodal visual information, 3D visual information, visual information enhancement and visual information quality assessment.He would have achieved in-depth knowledge of one of these core areas through independent study.He would have the ability to discuss (i.e. to describe, analyze, reason about and implement) how digital visual information may be represented, processed, encoded and transmitted.

Skills:Make appropriate use of mathematical techniques in visual information processing and analyses. Demonstrate on a usecase by implementing techniques such as DL-based adaptive algorithms, scalable approaches and real-time techniques to solve problems in visual information processing.

General competences: Be able to review scientific publications from interdisciplinary areas related to visual information processing and analyses: e.g., 3D and multi-view visual information visualisation, object detection, multitarget tracking, activity recognition, volumetric video and point cloud visualization, processing and interaction, and propose new approaches for such application areas.

The candidate has the ability of appreciation of the impact of (i.e. to describe, analyze, reason about) recently published research in visual information processing and its sustainability potential and concerns.

Learning methods and activities

We will have seminars using a blended learning approach with a mix of conventional lectures given by the course responsible and invited experts in addition to student presentations. The students will work individually or in groups on assigned topics.

All lectures and students presentations are considered part of course.

Further on evaluation

Final project report in addition to giving 2 presentations consisting of an introductory lecture (20 min) and a full lecture (45 min). The first on the bases of the term paper (literature review and research questions) and the second based on the final project report. Attend at least 80% of the lectures and seminars.

Specific conditions

Recommended previous knowledge

Background knowledge in visual information processing and analysis. Such as courses on image and video processing, 3D information representation and analysis, volumetric data visualisation and interaction, etc.

Required previous knowledge

Basics of image processing and programming.

Course materials

Recent research papers, online tutorial/GitHub links, and lecture slides. Research papers and other relevant teaching material used in the seminars will be made available electronically.