Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

Project Hot Topics in Computer Vision B (6 LP)Module description #40048 / Version 4

← Module page Deutsche Fassung
This module description is not valid in the current semester (Winter semester 2026/27).
Module / Version#40048 / #4
ValiditySS 2016 – WS 2016/17
Available language(s)English
Credit points6
Person responsible for the moduleHellwich, Olaf
GradingGraded
Exam formatPortfolio examination
Language(s) of instructionEnglish

Affiliation

FacultyFakultät IV
InstituteInstitut für Technische Informatik und Mikroelektronik
Academic chair34341600 FG Computer Vision and Remote Sensing

Contact

OfficeNot specified
Contact personNot specified
E-mail addressNot specified
WebsiteNot specified

Learning outcomes

Project title: "Scientific Process in Computer Vision: From Ideas to Publications"

Participants will gain significant insights into computer vision related problems and solutions. The goal is not to explore the whole field of research completely, but rather to confront the participants with the full complexity of one specific problem and to challenge their own initiative. Therefore we do not provide a
pedagogically gentle introduction of the learners to the scientific area, but we allow insights and participation in research and development. The ability of the participants to work in a team shall be improved by this module.

Content

The process of creating a contribution to the knowledge or to the tools of the scientific community is nearly independent from the specific field of research or application. Starting from an innovative idea, the novelty of the idea has to be investigated, the abstract idea has to be modeled, implemented, evaluated and finally described in a precise and comprehensible manner.

During the project this scientific process will be explored on examples of computer vision tasks. Small project teams will handle the whole process starting from provided ideas to a final summary of the scientific findings. The project is divided into four parts:

Part I: During the initial modelling phase, ideas are explored, extended and concretized. The participants assign themselves to project teams and select one of the proposed ideas. The performance evaluation of this first part is based on active participation, meaningful contributions to the discussion, as well as a preliminary summary of the conclusions including a priority list of ideas favoured by the student.

Part II: During the second step, the selected ideas are further concretized and put into the context of state-of-the-art. Furthermore, a coarse framework for implementation and evaluation has to be developed. The performance evaluation of this second part is based on a presentation as well as a written report
about the state-of-the-art and the general design of implementation and evaluation of the selected idea.

Part III: During the third step, the selected ideas will be implemented and evaluated. The performance evaluation of this third part is based on a presentation about the implementation and evaluation, and last but not least the well documented code.

Part IV: During the last step, the selected ideas, their implementation and evaluation will be described.

The report has to be compiled according to scientific standards. Additionally, the reports of all teams will be reviewed by other teams to further improve the quality. The performance evaluation of this last part is based on a written report about the implementation and evaluation. If the scientific contribution of the team to state-of-the-art is significant enough, it will be considered for publication in suitable conferences/journals.

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Hot Topics in Computer Vision BProject0433 L161 Winter and summer semester–6 ISIS

Workload and credit points

Hot Topics in Computer Vision B (Project)

Workload descriptionMultiplierHoursTotal
Attendance156 h90 h
Preparation/ Post-processing156 h90 h
180 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 participants explore basics and advanced issues of the field.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Knowledge from the modules "Digital Image Processing" or "Automatic Image Analysis" or "Photogrammetric Computer Vision".

Mandatory requirements for the module examination registration:

This module has no examination requirements.

Completion of the module

GradingGraded
Exam formatPortfolio examination
LanguageEnglish

Test elements

NamePoints/WeightCategoryDuration/Extent
Presentation P210
Presentation P310
Software40
Summary P15
Written report P210
Written report P425

Exam description

In total 100 points can be achieved.
The final grade according to §47 (2) AllgStuPO is calculated based on grading key 1 of faculty IV.

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: Winter and 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://isis.tu-berlin.de

Recommended literature

No recommended literature given

Assigned programs

This module is not used in any program.

Nebenhörerinnen / Nebenhörer können an der Veranstaltung teilnehmen.

Miscellaneous

The module "Project Hot Topics in Computer Vision " is offered each term.