FP6 - CARETAKER
Content Analysis and Retrieval Technologies to Apply Knowledge Extraction to Massive Recording
CLIENT: European Commission, as a Multitel Research Engineer
DESCRIPTION
Project initiated in the context of the European FP6 Program.
From the official description:
“The CARETAKER project aims at studying, developing and assessing multimedia knowledge-based content analysis, knowledge extraction components, and metadata management sub-systems in the context of automated situation awareness, diagnosis and decision support. More precisely, CARETAKER will focus on the extraction of a structured knowledge from large multimedia collections recorded over networks of camera and microphones deployed in real sites. The produced audio-visual streams, in addition to surveillance and safety issues, could represent a useful source of information if stored and automatically analyzed, in urban planning and resource optimization for instance.
CARETAKER will model and account for two types of knowledge: on one side, the multi-user knowledge (safety operators, decision makers), represented by their needs, their use-case scenario definition, and their abilities at providing context description for sensory data; on the other side, the content knowledge, characterized by a first layer of primitive events that can be extracted from the raw data streams, such as ambient sounds, crowd density estimation, or object trajectories, and a second layer of higher semantic events, defined from longer term analysis and from more complex relationships between both primitive events and higher-level events. Both knowledge types will be modelled through ontologies and exploited in the content extraction methodologies. The latter will be based on an innovative approach, whereby probabilistic models will be associated with each ontological entity, allowing to take full advantage of both statistical data-driven and scenario-based reasoning approaches, allowing for effectiveness, flexibility, and robustness with respect to sensor deployment conditions. Extracted metadata will be incorporated in knowledge management systems providing web-base content access and semantic, spatio-temporal, automatic knowledge discovery retrieval capabilities.”
ROLE
As a Research Engineer, I was responsible for the development and integration of data exchange tools in C, C++ and Java into the internal development framework MVision.
