Automatic Image AnalysisModule description #40345 / Version 6
- 6 CP
- Written exam
- Graded
- Summer semester
- English
This module description is not valid in the current semester (Winter semester 2026/27).
Current version (v10)
| Module / Version | #40345 / #6 |
|---|---|
| Validity | SS 2019 – WS 2019/20 |
| Available language(s) | English |
| Credit points | 6 |
| Person responsible for the module | Hellwich, Olaf |
| Grading | Graded |
| Exam format | Written exam |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Technische Informatik und Mikroelektronik |
| Academic chair | 34341600 FG Computer Vision and Remote Sensing |
Contact
| Office | MAR 6-5 |
|---|---|
| Contact person | Hellwich, Olaf |
| E-mail address | olaf.hellwich@tu-berlin.de |
| Website | https://www.tu.berlin/cv |
Learning outcomes
The students acquire stepwise competence for the development of image understanding methods. According to computer vision paradigm knowledge-based image analysis methods are developed based on feature extraction. The module clarifies that the learned skills can be used within multifaceted application areas of automatic image understanding.
Content
Visual cognition, grouping, shape descriptors, computer vision paradigm, knowledge-based image analysis, models of the real world, formal representation of the models, modelling of uncertainty (softcomputing), invariant pattern recognition, Bayesian decision theorem, Markoff random field models, Bayesian networks, object categorisation, automatic interpretation of maps, application to close range and air photographs
Module components
Compulsory area
The following courses are mandatory for this module:
Workload and credit points
Automatic Image Analysis (Lecture)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Preparation/ Post-processing | 15 | 2 h | 30 h |
| 60 h | |||
Automatic Image Analysis (Exercise)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Preparation/ Post-processing | 15 | 6 h | 90 h |
| 120 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
The lecture explains methods and algorithms, their underlying philosophy, as well as mathematical foundations from a rather theoretical point of view. Participants are expected to rehearse topics after class in preparation for the exercises.
The exercises take place in parallel. They rehearse methods and algorithms from a more practical point of view, introduce variations and extensions, and discuss implementation details of the homework assignments.
Homework assignments are given during the exercises and must be solved within two weeks. These assignments cover theoretical questions as well as programming exercises and are solved by working in small groups of three to four students.
The exercises take place in parallel. They rehearse methods and algorithms from a more practical point of view, introduce variations and extensions, and discuss implementation details of the homework assignments.
Homework assignments are given during the exercises and must be solved within two weeks. These assignments cover theoretical questions as well as programming exercises and are solved by working in small groups of three to four students.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Knowledge according module „Digital Image Processing" or equivalent is preferable.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Written exam |
| Language | English |
| Duration/Extent | 90 minutes |
Exam description
A written examination at the end of the term. Conditions of accreditation are passed exercises.
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Summer semester.
Maximum number of participants
This module is not limited to a number of students.
Registration procedures
Registration for the exam has to be made online.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
available – https://www.isis.tu-berlin.de
Recommended literature
- http://www.cv.tu-berlin.de/menue/lectures/summer_term/automatic_image_analysis/parameter/en/
Assigned programs
This module is not used in any program.
Nebenhörerinnen / Nebenhörer können an der Veranstaltung teilnehmen.
Miscellaneous
The module is offered each summer term.