Moses - Bio-inspired Computer Vision

Display language

To modulepage Generate PDF

Module / Version:
#41001 / #1

Validity:
Seit SoSe 2020

Default display language:
English

Module title:
Bio-inspired Computer Vision

Credits:
9

Responsible person:
Maertens, Marianne

Grading:
benotet

Type of exam:
Portfolioprüfung

Zugehörigkeit

Faculty:
Fakultät IV

Institute:
Institut für Technische Informatik und Mikroelektronik

Area of expertise:
34341900 FG Computational Psychology

Prüfungsausschuss:
No information

Kontakt

Office:
MAR 5-5

Contact person:
Gallego, Guillermo

E-mail address:
marianne.maertens@tu-berlin.de

Website:

http://www.psyco.tu-berlin.de/

Learning Outcomes

Students have an in-depth understanding of selected early vision models of human perception and their implementation in hardware (neuromorphic cameras). They are able to present and convey the acquired knowledge and skills eloquently.

Content

The project topic is subject to change, and will be made available before the start of each semester. Please see: http://www.psyco.tu-berlin.de/teaching.html

Module Components

Pflichtgruppe:

All Courses are mandatory.

Course Name	Type	Number	Cycle	Language	SWS	VZ
Bio-inspired Computer Vision Project	PJ	3434 L 10617	SoSe	English	6

Workload and Credit Points

Bio-inspired Computer Vision Project (PJ):

Workload description	Multiplier	Hours	Total
Attendance	15.0	6.0h	90.0h
Pre/post processing	15.0	12.0h	180.0h
			270.0h(~9 LP)

The Workload of the module sums up to 270.0 Hours. Therefore the module contains 9 Credits.

Description of Teaching and Learning Methods

Students are given an overview of the fundamentals and recent developments in the fields of early human vision and neuromorphic sensors. This overview will be paired with introductory exercises which will be guided by the course instructors and will involve programming examples to get familiar with the tools used for the team project. After the introductory sessions students work in small teams on one or two chosen topics. The teams implement recent research papers and present insights and results in progress talks. Throughout the course students will be enabled to work more and more independently. The final documentation of students’ work will be in the form of a project website.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Curiosity to learn something new. Eagerness to work in a team. Knowledge in the following domains is desirable: - image processing and/or computer vision - scientific computing (linear algebra, calculus, etc.) - machine learning - algorithms/data structures

Mandatory requirements for the module test application:

This module has no requirements.

Module completion

Grading

graded

Type of exam

Portfolio examination

Type of portfolio examination

100 Punkte insgesamt

Language

English

Test elements

Name	Points	Categorie	Duration/Extent
Implementation	50	practical	Programming projects
Presentation 1	15	flexible	approx. 15 minutes (presentation + questions)
Presentation 2	15	flexible	approx. 15 minutes (presentation + questions)
Documentation	20	flexible	Website

Grading scale

Notenschlüssel »Notenschlüssel 1: Fak IV (1)«

Gesamtpunktzahl	1.0	1.3	1.7	2.0	2.3	2.7	3.0	3.3	3.7	4.0
100.0pt	86.0pt	82.0pt	78.0pt	74.0pt	70.0pt	66.0pt	62.0pt	58.0pt	54.0pt	50.0pt

Test description (Module completion)

In compliance with § 47 (2) AllgStuPO, the overall grade is calculated according to the scoring system 1 of the Faculty IV. Implementation and project documentation should be done in English. Presentations can be done in German or English. 1. Implementation: The students work on one or two chosen papers and develop an approximate implementation of the paper. 2+3. Presentations 1 + 2: The students present a summary of the chosen papers and their implementation work and provide answers to questions from the audience. 4. Project documentation: The students summarize their final findings and results in a website.

Duration of the Module

The following number of semesters is estimated for taking and completing the module:
1 Semester.

This module may be commenced in the following semesters:
Sommersemester.

Maximum Number of Participants

The maximum capacity of students is 15.

Registration Procedures

Info on how to register for the course will be made available in the corresponding ISIS course and on the following website: http://www.psyco.tu-berlin.de/teaching.html

Recommended literature
Event-based Vision: A Survey. Gallego et al., arXiv 2019.
Snowden, R., Thompson, P., Troscianko, T. (2012). Basic Vision: An Introduction To Visual Perception Oxford University Press.
Vision Models for High Dynamic Range and Wide Colour Gamut Imaging: Techniques and Applications, Academic Press 2019.
Digital Image Processing, Gonzalez and Woods. Pearson
List of resources: https://github.com/uzh-rpg/event-based_vision_resources

Assigned Degree Programs

Semester:

Zeige auch ausgelaufene Studiengänge und StuPOs

This module is used in the following Degree Programs (new System):

Studiengang / StuPO	StuPOs	Verwendungen	Erste Verwendung	Letzte Verwendung
Computer Engineering (M. Sc.)	1	27	SoSe 2020	SoSe 2024
Computer Science (Informatik) (M. Sc.)	1	27	SoSe 2020	SoSe 2024
Elektrotechnik (M. Sc.)	1	18	SoSe 2020	SoSe 2024
Information Systems Management (Wirtschaftsinformatik) (M. Sc.)	1	9	SoSe 2020	SoSe 2024
Wirtschaftsingenieurwesen (M. Sc.)	1	10	SoSe 2020	SoSe 2024

Miscellaneous

FG also in Robotic Interactive Perception e-mail: guillermo.gallego@tu-berlin.de

Bio-inspired Computer Vision