Skip to main content
Go to the home page of the European Commission (opens in new window)
English English
CORDIS - EU research results
CORDIS
Content archived on 2024-06-16

Content Analysis and REtrieval Technologies to Apply Knowledge Extraction to massive Recording

Project description


Semantic-based knowledge systems
Targeted extraction of data from multimedia

Video surveillance is in common use all over the world. Advances in sensor devices, communications and storage capacities have made it increasingly easy to store large quantities of data. However, this data would be of much more value if the knowledge contained therein could be effectively exploited while at the same time preserving the privacy of the individual.

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.

Fields of science (EuroSciVoc)

CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.

You need to log in or register to use this function

Topic(s)

Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.

Call for proposal

Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.

FP6-2004-IST-4
See other projects for this call

Funding Scheme

Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.

STREP - Specific Targeted Research Project

Coordinator

THALES COMMUNICATIONS SA
EU contribution
€ 749 464,00
Total cost

The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.

No data

Participants (8)

My booklet 0 0