News

At the constituent meeting of the newly elected Institute Council on June 23, 2021, Prof. Alexander Raake (Audiovisual Technology Group) was elected as the new Director of the Institute of Media Technology (IMT).

Jun.-Prof. Dr. Matthias Hirth (User-Centered Analysis of Multimedia Data Group) was elected as his deputy.

The CO-HUMANICS project (Co-presence of people and interactive companions for seniors) started on June 1, 2021. Five TU Ilmenau groups are involved in this project, which is funded by the Carl Zeiss Foundation with 4.5 million euros. A total of eleven new employees will work on the project.

CO-HUMANICS website

As a member of the project team, M.SC. Luljeta Sinani started her work in the group.

In spring 2021, the realization of the ILMETA large-scale facility was started by the group, in which the first orders will be triggered.

At the beginning of 2020, the German Research Foundation (DFG) positively reviewed the application of the department for co-financing of the ILMETA large-scale facility. The DFG and the Free State of Thuringia then provide a total of € 570,000 for the realization of this infrastructure project.

New Publication

Steve Göring, Rakesh Rao Ramachandra Rao, Bernhard Feiten, and
Alexander Raake
"Modular Framework and Instances of Pixel-based Video
Quality Models for UHD-1/4K."
IEEE Access. vol. 9. 2021.
(https://ieeexplore.ieee.org/document/9355144)

Abstract

The popularity of video on-demand streaming services increased tremendously over the last years. Most services use http-based adaptive video streaming methods. Today’s movies and TV shows are typically recorded in UHD-1/4K and streamed using settings attuned to the end-device and current network conditions. Video quality prediction models can be used to perform an extensive analysis of video codec settings to ensure high quality. Hence, we present a framework for the development of pixel-based video quality models. We instantiate four different model variants (hyfr, hyfu, fume and nofu) for short-term video quality estimation targeting various use cases. Our models range from a no-reference video quality model to a full-reference model including hybrid model extensions that incorporate client accessible meta-data.

All models share a similar architecture and the same core features, depending on their mode of operation. Besides traditional mean opinion score prediction, we tackle quality estimation as a classification and multi-output regression problem. Our performance evaluation is based on the publicly available AVT-VQDB-UHD-1 dataset. We further evaluate the introduced center-cropping approach to speed up calculations. Our analysis shows that our hybrid full-reference model (hyfr) performs best, e.g. 0.92 PCC for MOS prediction, followed by the hybrid no-reference model (hyfu), full-reference model (fume) and no-reference model (nofu). We further show that our models outperform popular state-of-the-art models. The introduced features and machine-learning pipeline are publicly available for use by the community for further research and extension.