Associate team GOP – Graph-based Omnidirectional video Processing
Due to new camera types, the format of the video data has become more complex than simple 2D images or videos as it was the case a few years ago. In particular, the omnidirectional cameras provide pixels on a whole sphere around a center point and enable a vision in 360°. In addition to the fact that the data size explodes with such cameras, the inherent structure of the acquired signal fundamentally differs from the 2D images, which makes the traditional video codec obsolete. In parallel of that, an important effort of research has been lead recently, especially at EPFL, to develop new processing tools for signals lying on irregular structures (graphs). It enables in particular to build efficient coding tools for new types of signals. The proposed research project will actually study how graphs can be built for defining a suitable structure on one or several 360 videos and then used for compression. The collaboration between SIROCCO (Inria) and LTS4 (EPFL) has been very active in the recent years. However, only one-to-one collaboration was involved. When opening these new ambitious research direction, the project GOP will involve more than two or three researchers, and build a bidirectional collaboration between different people of the SIROCCO and LTS4 teams.
Keywords: Omnidirectional cameras, Graph-based signal processing, image compression