Projects
Video Processing for Multiview Multimodal Camera Systems Ghent University
Free viewpoint (multiview) video aims at enabling virtual navigation in a dynamic 3D scene from
arbitrary camera locations and orientations. The associated technologies also signify the solution to
the problem of providing genuinely immersive “lasses-free”3D media, offering not only stereopsis,
but also motion parallax. Capturing high-quality multiview content from real-world scenes is an
enormous ...
Compression History Discovery through Video Range Decoding for Fake Video Detection Ghent University
Imagine a video of Zelenskyy on the internet in which he makes false statements. This would have devastating consequences, yet it could be fake. Is it really the President, or is it a fake? This proposal aims to answer this question. To detect manipulation, we exploit “compression history fingerprints”. This concept considers that fake regions typically underwent a different amount of compression steps, e.g., if a fake face was added to a ...
Advanced techniques for distributed video coding Vrije Universiteit Brussel
Advanced Scalable Video Coding Vrije Universiteit Brussel
Towards natural brain-computer interfaces: representation learning for identifying the temporal encoding of realistic video footage in EEG KU Leuven
Brain-computer interfaces (BCIs) facilitate interaction between the brain and a computer or machine. Electroencephalography (EEG) is by far the most popular non-invasive BCI modality, because it is cheap, mobile, and it has an excellent temporal resolution to track neural responses that are time-locked to a sensory stimulus. However, traditional BCI paradigms heavily rely on synthetic and controlled sensory stimuli and an active participation ...
Advanced Scalable Video Coding. Ghent University
H,264/AVC and H,264/SVC currently represent the state-of-the-art in video coding technology. Recent research show that the compression efficiency of H.264/AVC for current sources (HD) is far from satisfactory. On top of this, many fundamental research directions in video coding have not been sufficiently explored in current standards. This project will therefore focus on novel techniques for spatial prediction, exploitation of spatial ...
Advanced techniques for distributed video coding Ghent University
In contrast to conventional video compression, distributed video coding (DVC) offers low-complexity encoding at the cost of high-complexity decoding. Since DVC compression performance is still quite low, this project aims to improve compression through more accurate correlation noise modeling, advanced prediction techniques, and additional coding modes, while taking into account constraints on network bandwidth, complexity, and delay.
Prediction of fire development in an enclosure, using compressed video data Ghent University
For the safety of people, it is important to predict flashover in case of a growing fire in a building compartment. With current calculation methods this is not yet possible. In this project, use will be made of images from security cameras. These data are treated in compressed format and sent to computers for analysis. By means of the analysis results and by means of, to be developed, simplified calculation methods, the fire development can ...
Performance analysis of queueing models with AQM for scalable video Ghent University
The aim of this project is to investigate the performance of active queue management techniques in the nodes of a packet swithced network. In particular, various queueing models will be constructed and analysed to assess the performance of transmission of layered video over these networks.