Digital video will bring more formats and opportunities leading to large-scale video assets for which the consumer and the professional will need advanced storage and search technology
Video plays a key role in information distribution and access and it will be the natural form of communication on the Internet and via mobile phones.
Current search engines, however, all rely on keyword-based access and do not allow semantic search.
The VIDI-Video project aims to integrate and develop state of the art components from machine learning, audio event detection, video processing, interaction and visualization into a fully implemented audio-visual search engine combining large number of categories and exploiting the interclass similarities as well as using the information from different sources: metadata, keyword annotations, audio visual data, speech, and explicit knowledge.
VIDI-Video is performing extensive experiments in each field of specialisation to optimize the parameters and classification performance based on the classification methods chosen for the final system.
VIDI-Video project will substantially enhance access to video, by developing a semantic search engine.
The project will boost the performance of video search by developing a 1000 element thesaurus for automatically detecting instances of semantic concepts in the audio-visual content. The main novelties of VIDI-Video are the size and quality of the thesaurus.
The VIDI-Video project is a FP6 project funded by the EU.
There will be a significant impact on indexing and retrieval practices currently employed especially by broadcasting archivists.
The broadcasting community as a whole will benefit from the project, since it is expected that a sophisticated set of software tools for broadcast video annotation and retrieval will be made available.
The secondary effect of video search engines will be even bigger with applications in surveillance, conferencing, event reconstruction, diaries, and cultural heritage documentaries.