M4 / September Integrating multimodal descriptions to index large video collections M4 meeting – Munich Nicolas Moënne-Loccoz, Bruno Janvier, Stéphane Marchand-Maillet and Eric Bruno Viper group Computer Vision & Multimedia Laboratory University of Geneva
M4 / September Outline i. Motivations ii. Modelling video documents iii. Indexing video documents iv. Retrieving video documents v. ViCoDE interface demonstration vi. Conclusion
M4 / September Motivations Video Documents End-User Indexing framework Querying Storing Storing & Querying video documents Integrate multimodal descriptions Efficient retrieval algorithms ?
M4 / September Motivations MPEG-7 multimedia documents model Standard Weak ontology support Native XML-Database storage Document-centred Inefficient cross documents multidimensionnal indexing
M4 / September Generic Data Model Relational DBMS Raw Data Access External Indexing & Retrieval Processor Indexing Framework OVAL MaxDB DBMS Indexing Processor Overview Data Model
M4 / September Document Model Subset of MPEG-7 model MPEG-7 compliance (XML-enabled model) Temporal Segments Central Data Unit (Data-centred model) Ontology Capabilities W3C-Ontology Web Language compliant Feature Space Indexing structures
M4 / September Document Model Description Structure Information DocumentMedia Stream Temporal Segment OntologyAnnotationDescriptorFeature Space Index Composed by Role Uses
M4 / September Document Storage Videos Documents : TRECVid-2003, MPEG-7, IM2/M4 Corpus ~ 100 hours MPEG-1 Videos Semantic Descriptions : TRECVid-2003 Annotations, Manual Annotations Multimodal feature-based descriptions : Shot segmentation Global color & motion histogram Activity descriptors (Wavelet motion, Salient Regions) ASR histogram Audio descriptors
M4 / September Document Index Document meta-data & structure DBMS Access Facilities (SQL queries, Query optimization, Indexes) Document raw-data Object-based Video Access Library (C++, Java, Matlab) Exact and Random access to media stream raw data Plugins based (MPEG-1, MPEG-2)
M4 / September Document Index Document descriptions External Indexing Semantic Description Use of ontology structure Feature Based Description Multi-dimensional index structure ( Distance Matrix, Vantage Point Tree … ) Index processor : MATLAB Index file Index Processor Index Data Access Script Query Data
M4 / September Document Retrieval Multiple feature spaces relevance feedback Set of positive & negative examples : Set of feature space distances : Look for the best linear combination of distances according to the user query: ?
M4 / September Document Retrieval Linear discriminant analysis Ranked result : Relevance feedback loop ?
M4 / September Video Content Description & Exploration Front-end prototype of the presented framework Java Server Page web content generation OVAL based on the fly generation of the Key-Frame Matlab indexing and retrieval algorithm ViCoDE demo ViCoDE
M4 / September Conclusion Generic Multimedia Documents Management Framework Generic multimedia document model - MPEG-7 compliant Standard ontology support Generic Multimodal indexing & Retrieval engine Integration of meeting features Content based querying of meeting collections ? Questions ?