K-Space WP3

Research Activities

Integration Activities

Content-based Multimedia Analysis

Knowledge Extraction

Semantic Multimedia

K-Space Framework for Integration of software tools

Dissemination

K-Space Web Management Tool

(Private Site)

Content Based Multimedia Analysis

(Work Package 3)

Research into tools and methodologies for low- and mid-level audiovisual multimedia content analysis will be conducted. The target is to tackle the semantic gap in a bottom-up approach, i.e. adapting low-level techniques for knowledge-based multimedia analysis. For the results of these analysis algorithms suitable descriptors or description schemes for MPEG-7 or other appropriate description standards will be developed. The concrete work is structured into four activities: content structuring, moving 2D and 3D object segmentation and indexing, audio/speech processing and text analysis and content description. The information provided by this WP will be used in WP4 "Knowledge Extraction" and WP5 "Semantic Multimedia" to gain higher-level information from the extracted low- to mid-level information. The developed tools will utilize interfaces and infrastructure provided by WP6 "Integration" enabling efficient exchange of data and tools amongst different partners.

Activity WP3.1 - Content Structuring

Activity WP3.2 - Moving 2D and 3D Object Segmentation and Indexing

Activity WP3.3 - Audio/Speech Processing and Text Analysis

Activity WP3.4 - Content Description

Partners Involved

Joanneum Research Forschungsgesellschaft mbH, (JRS)

Queen Mary, University of London (QMUL)

Koblenz University, (Uni Ko-Ld)

German Research Centre for Artificial Intelligence (DFKI)

Informatics and Telematics Institute (ITI) & Centre for Research and Technology Hellas (CERTH)

Dublin City University, (DCU)

Centrum voor Wiskunde en Informatica, (CWI)