This website is no longer updated.

As of 1.10.2022, the Faculty of Physics has been merged into the TUM School of Natural Sciences with the website https://www.nat.tum.de/. For more information read Conversion of Websites.

de | en

Model based Evaluation of images and image sequences

Module IN2024

This Module is offered by TUM Department of Informatics.

This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.

Basic Information

IN2024 is a semester module in German or English language at Bachelor’s level and Master’s level which is offered in summer semester.

This module description is valid to WS 2012/3.

Total workloadContact hoursCredits (ECTS)
90 h 30 h 3 CP

Content, Learning Outcome and Preconditions

Content

A camera observes its environment. To reconstruct from images or image sequences an internal representation of the three dimensional dynamic world is an extremely underdetermined problem. Additional knowledge about the world is mandatory for the solution. To seperate content and processing this knowledge is preferably formulated as declarative knowledge, represented as a model. Topics of the lecture are:

- priniples of model based systems
- overview of applications in research, medicine, industry ...
- levels of knowledge abstraction
- knowledge representation and models
- inference methods
- iconic, symbolic, and semantic models
- exemplary systems and current research

Learning Outcome

It is a challenging problem to reconstruct from images or image sequences an internal representation of the three dimensional dynamic world, which a camera observes. To solve this problem models of the real world are constructed and help to compensate the under-determinedness of the reconstruction problem. The students should conceive the role of such models in appoaches to understand the content of images or image sequences. They will study the theory of symbolic and stochastic modelling and will be able to analyse exemplary applications. They should be able to program simple image or image sequence understanding systems.

Preconditions

IN2016 Image Understanding II: Robot Vision

Courses, Learning and Teaching Methods and Literature

Learning and Teaching Methods

lecture

Media

no info

Literature

Will be announced in the lecture

Module Exam

Description of exams and course work

oral exam

Exam Repetition

The exam may be repeated at the end of the semester.

Top of page