3DTVS (FP7-287674) (3DTV Content Search) is a Collaborative Project, that started on November 1st, 2011 and it is scheduled to run for 36 months. In 3DTVS there are 7 partners from 3 countries representing Universities, Research Institutions and Industry.
The goal of the 3DTVS project is to devise scalable 3DTV AV content description, indexing, search and browsing methods across open platforms, by using mobile and desktop user interfaces and to incorporate such functionalities in 3D audiovisual content archives. The major novelty in 3DTV content indexing/retrieval research will be on how to exploit 3D (depth) information for stereo and multiview video indexing, retrieval and browsing that could address semantic queries of the form ‘find stereo videos with shallow depth’ or ‘find stereo videos, where actor X approaches actor Y’. 3D multichannel audio analysis will perform better audio source (e.g. musical instrument) separation and localization that will be used in 3D audio/cross-modal indexing and retrieval. Multimodal 3D audiovisual content analysis will built on the results of 3D video and audio analysis. 3DTV content description and search mechanisms will be developed to enable fast reply to semantic queries. User friendly mobile/desktop search interfaces will be built that could also permit adaptation to the user needs and profile. The novel results that will be generated within 3DTVS will: