Summer School 2020
Deep Learning in Image and Video Processing
Within this course, we want to explore Image and Video Processing tasks boosted by Deep Learning methods. These methods gain more and more attraction in the scientific environment driven by their continuing success in solving a plethora of diverse signal processing tasks. Especially in the field of image and video processing, deep learning methods are able to greatly improve over existing algorithms and to solve entirely new tasks that were deemed intractable using classical approaches.
Possible areas of application are numerous. From artistic applications like coloring black-and-white videos, generating deceptively real fake images or transferring the style of one image to another, to industrial applications like image super-resolution, frame rate up-conversion or object detection and object tracking for surveillance and autonomous driving, deep learning based image and video processing has widespread impact.
This course offers an overview of classical image and video processing algorithms, an introduction to deep learning and discusses various practical applications. It is organized in two parts. In part 1, each participant will give a presentation of around 30 minutes on a selected topic. In part 2, the participants will work together on the development of a small scale self-driving car implementing classical and deep-learning based image and video processing algorithms.
The course takes place within the scope of the Summer School 2020 (20.09.2020 – 02.10.2020) in the Sarntal Alps (South Tirol). It aims at students at late Bachelor-level and Master-level. Due to the extensive programming part, an advanced level in programming is required.
The results of the exam 'Kommunikationsnetze (KONE)' are now available in 'meinCampus'.
The date of inspection is on Wednesday, 25th March 2020 at 8:30 a.m. in room 06.025.
Update: Due to the restricted university services during the Corona crisis, the date of inspection will be presumably postponed to May. More information will follow.
Seminar Summer Semester 2020
Selected Topics in Multimedia Communications and Signal Processing
Audio Signal Processing for Human-Robot Interaction
Prof. Dr.-Ing. Walter Kellermann; Dr.-Ing. Heinrich Löllmann; Alexander Schmidt, M.Sc.
The acceptance of robots in our daily life will largely depend on how well a robot is aware of its environment and how responsive it can react to any kind of human expression. With acoustic signals revealing a rich amount of information about the environment and speech being the most effective means of communication between humans, robots must be able to analyze the acoustic scene and use voice communication in a natural way.
In this seminar, state-of-the-art concepts and methods for an intuitive audio-signal-based human-machine interaction for robots are discussed. This task is especially challenging since a robot typically operates in adverse acoustical environments characterized by noise, interfering sources and reverberation. Therefore, efficient and robust methods for acoustic scene analysis and signal enhancement are required, including localization, extraction and separation of acoustic sources, as well as and very specific for robots, the reduction of self-noise. Being typically equipped with other sensor modalities beside microphones, sensor fusion is also highly relevant.
Reflecting the current trend in research in this domain, many of the topics of this seminar are based on methods from artificial intelligence and machine learning.
This seminar is designed for Bachelor and Master programs in Electrical Engineering, Electronics and Information Technology (EEI), Information and Communication Technology (IuK), Industrial Engineering and Management (WING), Computational Engineering (CE), Communications and Multimedia Engineering (CME), Advanced Signal Processing and Communications Engineering (ASC) as well as related study programs.
The seminar consists of three mandatory meetings:
1st meeting (late April 2020): An introduction will be given and the individual topics are assigned to the participants.
2nd meeting (early June 2020): The participants will give a brief presentation about the status of their work and hints for the final presentation are given.
3rd meeting (mid July 2020): Each participant will give a presentation of 25 minutes and submit a report on his/her topic of 10 to 15 pages.
All meetings and presentations will be given in English and the reports are expected to be written in English.
Registration & Contact
Registration for this seminar via the central registration platform of the Department EEI: https://www.studon.fau.de/xcos2828315.html (March 30-April 5).
In total, we offer 12 seminar places. For questions and further information, contact email@example.com.
The following topics will be offered:
→ Aspects of Reinforcement Learning with Applications to Audio Signal Processing
→ MM- and EM-Algorithm: Concepts and Applications
→ Sound Source Position Estimation in Robotics
→ Sound Source Tracking for Robots
→ Active Localization and Exploration
Signal Extraction and Enhancement
→ Blind Source Separation for Robots
→ Ego-noise: Characteristics and Suppression Methods
Classification, Detection and Understanding
→ Acoustic Event Classification for Robotics
→ Privacy for ASR and Scene Classification
Sensor Data Fusion
→ General Concepts for Sensor Data Fusion
→ Audio-visual Signal Enhancement/Audio-visual Tracking
Microphone Array Design
→ Optimal Microphone Placement
Three graduates of the LMS received the Siemens award for their thesis works.
- Frank Sippel received the Siemens Master Thesis Award for his thesis work entitled Estimation of Light Spectra fromMultispectral Images.
- Martin Müller received the Siemens Master Thesis Award for his thesis work entitled Development of Al-based Models for the Evaluation of Speech Quality.
- Anna Meyer received the Siemens Bachelor Thesis Award for her thesis work entitled Chrominanz-Unterabtastung von Screen Content Daten im Transformationsbereich.
The awards were conferred during the graduation ceremony of the Technical Faculty on Feb. 2, 2020.
We are searching for a motivated and highly skilled PhD student for the topic “Image and video analytics for anomaly detection in industrial environments”, which is a project in cooperation with Siemens. A description of the position can be downloaded. Please send your applications to Prof. André Kaup or Sanjukta Gosh, Ph.D.
Der Beitrag “Intra Frame Prediction for Video
Coding Using a Conditional Autoencoder Approach” wurde auf dem Picture Coding Symposium, Ningbo, China, 12-15 November
2019 mit dem Best Paper Award ausgezeichnet.
for the contribution "Sparse Adaptation of Distributed Blind Source Separation in Acoustic Sensor Networks"
- Master Thesis, Final Lecture
- 13.11.2019 at 10am
- Room: 06.025
The winners won the Best Paper Award for the article "Power Modeling for Virtual Reality Video Playback Applications" at the International Symposium on Consumer Technologies (ISCT 2019).
Die Mitgliederversammlung des Universitätsbundes Erlangen-Nürnberg hat Prof. Dr.-Ing. André Kaup am 08.04.2019 in Ihren Beirat gewählt. Der Universitätsbund ist ein Zusammenschluss der Freunde und Förderer der FAU und versteht sich als Mittler zwischen den Belangen der Hochschule und den Interessen der Menschen und der Wirtschaft der nordbayerischen Region. Zu den rund 2.000 Mitgliedern zählen Studierende, Absolventen, Lehrende, Kommunen, Unternehmen und Privatpersonen aus allen Bereichen des gesellschaftlichen Lebens.
Dr.-Ing. Heinrich Löllmann wurde für die Jahre 2019 – 2021 zum Mitglied des Audio and Acoustic Signal Processing Technical Committe (AASP TC) der IEEE Signal Processing Society gewählt.
The "Forum Technologie" organizes public symposia on current scientific and technical questions and developments. With its symposia, the "Forum Technologie" wants to convey the fundamentals of technology and applied natural sciences in a comprehensible manner, strengthen technical confidence and reduce hostility to technology, discuss the effects of technical innovations on society and culture and provide technical advice to representatives from politics and administration.
The exercise for the course "Signale und Systeme II" by Dr.-Ing Christian Herglotz was ranked second best in the teaching evaluation of the summer term 2018 (average grade 1.32, 24 exercises were assessed, category ÜP20).