SlideShare una empresa de Scribd logo
1 de 20
Descargar para leer sin conexión
medialab




PISA – Proof of Concept
   Production, Indexing and Search of Audiovisual Material
PISA - Positioning

   ! VRT-Medialab (medialab.vrt.be) - technical R&D

   ! IBBT (www.ibbt.be) – Interdisciplinary Research Institute

   ! PISA – Research Project on Production and Indexing of Audiovisual Media
       ! 21 Man-year
       ! Computer Assisted Manufacturing
       ! Unsupervised Feature Extraction
       ! Search Engine Technology




                                                                               2
medialab
Context - Digital Media Production



                               Suprastructure – Metadata Mgnt




                              Production and distribution
                               Production and distribution
                                                 Editing                  Mastering




                                                               Media
                                             Ingest          Asset Mgnt       Playout




                               Infrastructure - Networks and Storage




                                                 Production Platform
                                                                                        3
medialab
Digital Asset Management, Content Management…




                               Suprastructure – Metadata Mgnt




                               Production and distribution




                               Infrastructure - Networks and Storage




                                                Production Platform
                                                                       4
medialab
User Expectations


                                Communication
                                 (Information)

                                  Data General                  Data General                  Data General
                                                                                                                            Suprastructure – Metadata Mgnt
                                                 Data General                  Data General                  Data General




                                                      Meta                                    Meta
                                                      Data                                    Data

                                                                                                                            Production and distribution


    Assumptions:
    • An item is relevant or it is not
    • A “scene” is the logical unit of search
                                                                                                                            Infrastructure - Networks and Storage
    The ideal search engine
    • retrieves all relevant items (recall 100%)
    • without false positives (precision 100%)
    • enables instant access to digital media
    • with respect to intellectual property.

                                                                                                                                             Production Platform
                                                                                                                                                                    5
medialab
Archiving – Disclosure, Annotation,…



                                                                           archiefnummer : ALG 20010813 1
                                                                           fragmentnummer : 1
                                                                           reeks      : 1000 ZONNEN EN GARNALEN
Opzoekscherm FILM               Set: 16 Aantal:        1                   bandnummer       : E03024404
blz 1 van 3                                                                formaat       : DBCM
 trefwoorden:     ibm and vrt                                              fragmenttitel : 1000 ZONNEN & GARNALEN
                                                                           beeld      : KL/PALPLUS
 archiefnummer:                                            -               fragmentduur    : 18 20
 uitzendjaar:                    maand:            dag:                    tekst     : 0'00quot; TOERISTISCH REPORTAGEMAGAZINE OVERZICHT
 fragmentnummer:                       fragmentduur:                                 ONDERWERPEN GENERIEK TOERISTISCH REPORTAGEMAGAZINE,
 reeks:                                                                              OVERZICHT ONDERWERPEN
 formaat:                       bandnummer:                                          0'50quot; VANDAAG : KUNSTENAAR LUC HOFKENS ONTWIERP EEN OASE
 aflevering:                    afleveringsnummer:                                   OP ZIJN DAKTERRAS IN BORGERHOUT DIE DOET DENKEN AAN DE
 programma:                       uitzenddatum:                                      GRAND CANYON INTERVIEW MET LUC EN ZIJN VROUW
 fragmenttitel:                                                                      MARILOU BUITENBEELD DAK MET OMGEVING BUITENKANT
 tekst:                                                                              ARBEIDERSWONING, PANO OVER ROTSWANDEN, KRATEN MET WATER,
 kategorie:                                                                          BEPANTING, FOTOALBUM MET VERLOOP WERKEN
 opnamedatum:                       opnamenummer:                                    4'00quot; JUNIOR : KLAARTJE ALAERTS, 13 JAAR WIL ASTRONAUTEN
 journalist:                    rechthebbende:                                       WORDEN ZE BEZOEKT HETEUROSPACE CENTER METRUIMTEVEREN,
                                                                                     RAKETTEN SIMULATIE IN RUIMTEVEER, INTERVIEW, HEEFT EEN
                                                                                     UFO GEZIEN MAAKT ZELF KLEIN RAKETJE, SCHIET HET AF
            SETS                                                                     7'50quot; DE SCHEURKALENDER : ARCHIEF RECLAMEFILM IBM
The strings required for the operation are not defined                               INTERVIEW MAURICE DE WILDE, EERSTE PERSOONLIJKECOMPUTER
                                                                           trefwoorden    : BELGIE; BORGERHOUT; ARTIEST; OASE; KUNST; GRAND
                                                                                     CANYON (NATUURGEBIED); DAK; TERRAS; INTERVIEW; EURO
 F11      F12     F13   F14      F17      F18     F19          F20   Ent             SPACE CENTER; RUIMTEVAART; PC; BOOTTOCHT; RIJKDOM;
Eindigen Sets Refset Toon Vorige Volg/Leeg Thesaurus Commando Opzoeken               PASSAGIER; GASTRONOMIE; RESTAURANT; PERSONEEL;
                                                                                     VAKANTIE; BINNENBEELD; SCHIP; BECKERS LEEN; VRT;
                                                                                     LOTTO; RADIOOMROEPSTER; KLANKSTUDIO; UITVINDING;
                                                                                     BARBECUE; BETONMOLEN; IBM; RECLAMESPOT
                                                                           rechthebbende : VRT




                                                                                                                                                6
medialab
Aha - The Search Engine!




                              7
medialab
Issues – Catch-22



     -> Automated processing of information is a key
        discriminator, but it requires correct and
        structured metadata

     -> “Annotation” of rich media requires semantic
        awareness and interpretation, and thus it is at
        best an approximation

     -> Product Engineering is the source of structured
        and meaningful information, but creative staff
        are not susceptible to technology




                                                          8
medialab
Objectives - Proof of Concept

                                          • One Set of Numbers(!)

                                          • Model Driven Development

                                          • Computer Assisted Manufacturing

                                          • Unsupervised Feature Extraction

                                          • Efficient Search and Retrieval



                                                      !
           Develop an extensible data-model and a consistent application
                    framework, accessible via an intuitive user-interface

                 (! Digitizing analogue and disintegrated information flows)
                                                                               9
medialab
Milestone 1 – Search Engine




                                    10
medialab
Milestone 1 – Search Engine
  !    Search federation by system integration                                 Search Client
  !    Facetted search                                                     (Custom Development)

  !    Integrated application of keywords
  !    Intuitive and structured presentation of results
  !    Direct access to audiovisual material




                       Legacy Video Library
                           (Basisplus)

                                              <NewsML-G2>

        Raw Material
      (EBU Superpop)                                           Media Asset                 Search Engine
                                                            Management System             (Lucene/SOLR)
                                                                (Ardome)



                       Actual news items
                           (Ardome)
                                                                                                           11
medialab
Shot Segmentation and Scene Recognition




                                                 12
medialab
Character Recognition




                              13
medialab
Video copy detection




                !   Identify dupplicates
                !   Generation tracking
                !   Grouping of search results
                !   Intellectual Property Protection



                                                       14
medialab
Milestone 2 – Feature Extraction
 ! Time-coded properties and indexing allow
   random access to material fragments:
      ! Shot segmentation and Keyframe extraction
      ! Subtitle processing and Speech recognition
      ! Taxonomy-driven topic detection
      ! Face recognition
      ! Scene recognition
      ! Copy detection

                               Legacy Video Library
                                   (Basisplus)

                                                 <NewsML-G2>

         Raw Material                                          Media Asset
       (EBU Superpop)                                          Management Asset
                                                                       Media                 Search Engine
                                                                    Management System       (Lucene/SOLR)
                                                                (Ardome)(Ardome)


                        Actual news items
                            (Ardome)
                                                                          Face
                                                                        Detection
                                                   Shot                                  Topic
                                                Segmentation                            Detection

         Media                                                           Speech
                                                                                                             15
medialab
      Production                                                       Recognition
Work in Process (due Q4 2008)


        !   Multi-lingual
        !   Access control and Intellectual Property Protection
        !   Audio segmentation and classification
        !   Music transcription
        !   Fractal-based visual indexing
        !   …




         Media                                                    16
medialab
      Production
Conclusion


      ! Enterprise search – structured metadata, limited number of libraries, limited number
        of records per library, dependencies between objects

      ! Intelligent search federation is aware of the media production process - scripts,
        webpages, subtitles and formal annotation may represent the same editorial object

      ! Random access to audiovisual material requires an index is based on timecode and
        not « wordposition in a document »

      ! Onthology-driven application logic is essential to create semantic awareness, i.e.
        resolving synonyms and disambiguation of homonyms

      ! The perfect search engine is not for sale yet and required from the ground up design
        and development.




                                                                                             17
medialab
Future Work - From « Metadata » to CAD/CAM




                                           ?
                                                   18
medialab
Future Work - From « Metadata » to CAD/CAM




                                           ?
                                                   19
medialab
! http://medialab.vrt.be/pisa
           ! http://projects.ibbt.be/pisa
           ! Maarten.verwaest@vrt.be

                                            20
medialab

Más contenido relacionado

Similar a Fiat 20080921 results PISA

search and retrieval of audiovisual material
search and retrieval of audiovisual materialsearch and retrieval of audiovisual material
search and retrieval of audiovisual material
vrt-medialab
 
Hybrid Publishing Consortium
Hybrid Publishing ConsortiumHybrid Publishing Consortium
Hybrid Publishing Consortium
Simon Worthington
 
Metadata om te creëren / Metadata to create
Metadata om te creëren / Metadata to createMetadata om te creëren / Metadata to create
Metadata om te creëren / Metadata to create
vrt-medialab
 
Metadata for video search: Trouvaille
Metadata for video search: TrouvailleMetadata for video search: Trouvaille
Metadata for video search: Trouvaille
vrt-medialab
 
Metadata to create and collect
Metadata to create and collectMetadata to create and collect
Metadata to create and collect
vrt-medialab
 
2007 EBU Training VRT Newsroom interoperability
2007 EBU Training VRT Newsroom interoperability2007 EBU Training VRT Newsroom interoperability
2007 EBU Training VRT Newsroom interoperability
European Broacasting Union
 
Cebit-2008: Content Aggregation
Cebit-2008: Content AggregationCebit-2008: Content Aggregation
Cebit-2008: Content Aggregation
David Nuescheler
 

Similar a Fiat 20080921 results PISA (20)

PISA - Proof of Concept
PISA - Proof of ConceptPISA - Proof of Concept
PISA - Proof of Concept
 
search and retrieval of audiovisual material
search and retrieval of audiovisual materialsearch and retrieval of audiovisual material
search and retrieval of audiovisual material
 
Digital Media Production
Digital Media ProductionDigital Media Production
Digital Media Production
 
Presentation of Scoop @Ebu Production Technology Seminar
Presentation of Scoop @Ebu Production Technology SeminarPresentation of Scoop @Ebu Production Technology Seminar
Presentation of Scoop @Ebu Production Technology Seminar
 
Hybrid Publishing Consortium
Hybrid Publishing ConsortiumHybrid Publishing Consortium
Hybrid Publishing Consortium
 
Digital Media Production
Digital Media ProductionDigital Media Production
Digital Media Production
 
Metadata om te creëren / Metadata to create
Metadata om te creëren / Metadata to createMetadata om te creëren / Metadata to create
Metadata om te creëren / Metadata to create
 
Metadata for video search: Trouvaille
Metadata for video search: TrouvailleMetadata for video search: Trouvaille
Metadata for video search: Trouvaille
 
Limecraft - Semantic Integration Platform
Limecraft - Semantic Integration PlatformLimecraft - Semantic Integration Platform
Limecraft - Semantic Integration Platform
 
Tape-less Workflow Applcation Architecture
Tape-less Workflow Applcation ArchitectureTape-less Workflow Applcation Architecture
Tape-less Workflow Applcation Architecture
 
Metadata to create and collect
Metadata to create and collectMetadata to create and collect
Metadata to create and collect
 
2007 EBU Training VRT Newsroom interoperability
2007 EBU Training VRT Newsroom interoperability2007 EBU Training VRT Newsroom interoperability
2007 EBU Training VRT Newsroom interoperability
 
IBM Smart Camp: Philippe Souidi on Big Data
IBM Smart Camp: Philippe Souidi on Big DataIBM Smart Camp: Philippe Souidi on Big Data
IBM Smart Camp: Philippe Souidi on Big Data
 
What every executive needs to know about IT
What every executive needs to know about ITWhat every executive needs to know about IT
What every executive needs to know about IT
 
Palestra 3 - Fabricação de moldes por micro-usinagem.
Palestra 3 - Fabricação de moldes por micro-usinagem.Palestra 3 - Fabricação de moldes por micro-usinagem.
Palestra 3 - Fabricação de moldes por micro-usinagem.
 
101 ab 1415-1445
101 ab 1415-1445101 ab 1415-1445
101 ab 1415-1445
 
101 ab 1415-1445
101 ab 1415-1445101 ab 1415-1445
101 ab 1415-1445
 
What's Next In An On Demand World
What's Next In An On Demand WorldWhat's Next In An On Demand World
What's Next In An On Demand World
 
What's hot in a flat world
What's hot in a flat worldWhat's hot in a flat world
What's hot in a flat world
 
Cebit-2008: Content Aggregation
Cebit-2008: Content AggregationCebit-2008: Content Aggregation
Cebit-2008: Content Aggregation
 

Más de vrt-medialab

Multischermenonderzoek
MultischermenonderzoekMultischermenonderzoek
Multischermenonderzoek
vrt-medialab
 
Taming your media chaos
Taming your media chaosTaming your media chaos
Taming your media chaos
vrt-medialab
 
Presentatie iMinds MediaCRM
Presentatie iMinds MediaCRMPresentatie iMinds MediaCRM
Presentatie iMinds MediaCRM
vrt-medialab
 
Evaluatiestudie VillaSquare
 Evaluatiestudie VillaSquare Evaluatiestudie VillaSquare
Evaluatiestudie VillaSquare
vrt-medialab
 
iMinds VillaSquare evaluation IBBT-SMIT
iMinds VillaSquare evaluation IBBT-SMITiMinds VillaSquare evaluation IBBT-SMIT
iMinds VillaSquare evaluation IBBT-SMIT
vrt-medialab
 
Multischermenonderzoek
MultischermenonderzoekMultischermenonderzoek
Multischermenonderzoek
vrt-medialab
 
Exploring your media with the Semantic Web
Exploring your media with the Semantic WebExploring your media with the Semantic Web
Exploring your media with the Semantic Web
vrt-medialab
 
Champ belgian broadcast_days
Champ belgian broadcast_daysChamp belgian broadcast_days
Champ belgian broadcast_days
vrt-medialab
 

Más de vrt-medialab (20)

Multischermenonderzoek
MultischermenonderzoekMultischermenonderzoek
Multischermenonderzoek
 
Browser as a broadcast medium
Browser as a broadcast mediumBrowser as a broadcast medium
Browser as a broadcast medium
 
Champ iMinds
Champ iMindsChamp iMinds
Champ iMinds
 
Taming your media chaos
Taming your media chaosTaming your media chaos
Taming your media chaos
 
Presentatie iMinds MediaCRM
Presentatie iMinds MediaCRMPresentatie iMinds MediaCRM
Presentatie iMinds MediaCRM
 
Evaluatiestudie VillaSquare
 Evaluatiestudie VillaSquare Evaluatiestudie VillaSquare
Evaluatiestudie VillaSquare
 
iMinds VillaSquare evaluation IBBT-SMIT
iMinds VillaSquare evaluation IBBT-SMITiMinds VillaSquare evaluation IBBT-SMIT
iMinds VillaSquare evaluation IBBT-SMIT
 
Building second screen TV apps
Building second screen TV appsBuilding second screen TV apps
Building second screen TV apps
 
Multischermenonderzoek
MultischermenonderzoekMultischermenonderzoek
Multischermenonderzoek
 
Exploring your media with the Semantic Web
Exploring your media with the Semantic WebExploring your media with the Semantic Web
Exploring your media with the Semantic Web
 
BDMA workshop presentation - Using the Second Screen - MediaSquare - MediaCRM
BDMA workshop presentation - Using the Second Screen - MediaSquare - MediaCRMBDMA workshop presentation - Using the Second Screen - MediaSquare - MediaCRM
BDMA workshop presentation - Using the Second Screen - MediaSquare - MediaCRM
 
Champ belgian broadcast_days
Champ belgian broadcast_daysChamp belgian broadcast_days
Champ belgian broadcast_days
 
Champ Pitch Celtic-Plus Event 2011
Champ Pitch Celtic-Plus Event 2011Champ Pitch Celtic-Plus Event 2011
Champ Pitch Celtic-Plus Event 2011
 
medialoep
medialoepmedialoep
medialoep
 
video for html5
video for html5video for html5
video for html5
 
html5 an introduction
html5 an introductionhtml5 an introduction
html5 an introduction
 
Boost your search with semantic technology
Boost your search with semantic technologyBoost your search with semantic technology
Boost your search with semantic technology
 
Media Square : platform for second screen experiences
Media Square : platform for second screen experiencesMedia Square : platform for second screen experiences
Media Square : platform for second screen experiences
 
MediaSquare - Check into your favourite media
MediaSquare - Check into your favourite mediaMediaSquare - Check into your favourite media
MediaSquare - Check into your favourite media
 
Transmedia
TransmediaTransmedia
Transmedia
 

Último

Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
UXDXConf
 

Último (20)

Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
 
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfWhere to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
 
Demystifying gRPC in .Net by John Staveley
Demystifying gRPC in .Net by John StaveleyDemystifying gRPC in .Net by John Staveley
Demystifying gRPC in .Net by John Staveley
 
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya HalderCustom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
 
Buy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdfBuy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdf
 
Intro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджераIntro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджера
 
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
 
Agentic RAG What it is its types applications and implementation.pdf
Agentic RAG What it is its types applications and implementation.pdfAgentic RAG What it is its types applications and implementation.pdf
Agentic RAG What it is its types applications and implementation.pdf
 
PLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. StartupsPLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. Startups
 
Optimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through ObservabilityOptimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through Observability
 
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfSimplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1
 
The Metaverse: Are We There Yet?
The  Metaverse:    Are   We  There  Yet?The  Metaverse:    Are   We  There  Yet?
The Metaverse: Are We There Yet?
 
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdfThe Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
 
What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024
 
How Red Hat Uses FDO in Device Lifecycle _ Costin and Vitaliy at Red Hat.pdf
How Red Hat Uses FDO in Device Lifecycle _ Costin and Vitaliy at Red Hat.pdfHow Red Hat Uses FDO in Device Lifecycle _ Costin and Vitaliy at Red Hat.pdf
How Red Hat Uses FDO in Device Lifecycle _ Costin and Vitaliy at Red Hat.pdf
 
ECS 2024 Teams Premium - Pretty Secure
ECS 2024   Teams Premium - Pretty SecureECS 2024   Teams Premium - Pretty Secure
ECS 2024 Teams Premium - Pretty Secure
 
FDO for Camera, Sensor and Networking Device – Commercial Solutions from VinC...
FDO for Camera, Sensor and Networking Device – Commercial Solutions from VinC...FDO for Camera, Sensor and Networking Device – Commercial Solutions from VinC...
FDO for Camera, Sensor and Networking Device – Commercial Solutions from VinC...
 
Speed Wins: From Kafka to APIs in Minutes
Speed Wins: From Kafka to APIs in MinutesSpeed Wins: From Kafka to APIs in Minutes
Speed Wins: From Kafka to APIs in Minutes
 
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
 

Fiat 20080921 results PISA

  • 1. medialab PISA – Proof of Concept Production, Indexing and Search of Audiovisual Material
  • 2. PISA - Positioning ! VRT-Medialab (medialab.vrt.be) - technical R&D ! IBBT (www.ibbt.be) – Interdisciplinary Research Institute ! PISA – Research Project on Production and Indexing of Audiovisual Media ! 21 Man-year ! Computer Assisted Manufacturing ! Unsupervised Feature Extraction ! Search Engine Technology 2 medialab
  • 3. Context - Digital Media Production Suprastructure – Metadata Mgnt Production and distribution Production and distribution Editing Mastering Media Ingest Asset Mgnt Playout Infrastructure - Networks and Storage Production Platform 3 medialab
  • 4. Digital Asset Management, Content Management… Suprastructure – Metadata Mgnt Production and distribution Infrastructure - Networks and Storage Production Platform 4 medialab
  • 5. User Expectations Communication (Information) Data General Data General Data General Suprastructure – Metadata Mgnt Data General Data General Data General Meta Meta Data Data Production and distribution Assumptions: • An item is relevant or it is not • A “scene” is the logical unit of search Infrastructure - Networks and Storage The ideal search engine • retrieves all relevant items (recall 100%) • without false positives (precision 100%) • enables instant access to digital media • with respect to intellectual property. Production Platform 5 medialab
  • 6. Archiving – Disclosure, Annotation,… archiefnummer : ALG 20010813 1 fragmentnummer : 1 reeks : 1000 ZONNEN EN GARNALEN Opzoekscherm FILM Set: 16 Aantal: 1 bandnummer : E03024404 blz 1 van 3 formaat : DBCM trefwoorden: ibm and vrt fragmenttitel : 1000 ZONNEN & GARNALEN beeld : KL/PALPLUS archiefnummer: - fragmentduur : 18 20 uitzendjaar: maand: dag: tekst : 0'00quot; TOERISTISCH REPORTAGEMAGAZINE OVERZICHT fragmentnummer: fragmentduur: ONDERWERPEN GENERIEK TOERISTISCH REPORTAGEMAGAZINE, reeks: OVERZICHT ONDERWERPEN formaat: bandnummer: 0'50quot; VANDAAG : KUNSTENAAR LUC HOFKENS ONTWIERP EEN OASE aflevering: afleveringsnummer: OP ZIJN DAKTERRAS IN BORGERHOUT DIE DOET DENKEN AAN DE programma: uitzenddatum: GRAND CANYON INTERVIEW MET LUC EN ZIJN VROUW fragmenttitel: MARILOU BUITENBEELD DAK MET OMGEVING BUITENKANT tekst: ARBEIDERSWONING, PANO OVER ROTSWANDEN, KRATEN MET WATER, kategorie: BEPANTING, FOTOALBUM MET VERLOOP WERKEN opnamedatum: opnamenummer: 4'00quot; JUNIOR : KLAARTJE ALAERTS, 13 JAAR WIL ASTRONAUTEN journalist: rechthebbende: WORDEN ZE BEZOEKT HETEUROSPACE CENTER METRUIMTEVEREN, RAKETTEN SIMULATIE IN RUIMTEVEER, INTERVIEW, HEEFT EEN UFO GEZIEN MAAKT ZELF KLEIN RAKETJE, SCHIET HET AF SETS 7'50quot; DE SCHEURKALENDER : ARCHIEF RECLAMEFILM IBM The strings required for the operation are not defined INTERVIEW MAURICE DE WILDE, EERSTE PERSOONLIJKECOMPUTER trefwoorden : BELGIE; BORGERHOUT; ARTIEST; OASE; KUNST; GRAND CANYON (NATUURGEBIED); DAK; TERRAS; INTERVIEW; EURO F11 F12 F13 F14 F17 F18 F19 F20 Ent SPACE CENTER; RUIMTEVAART; PC; BOOTTOCHT; RIJKDOM; Eindigen Sets Refset Toon Vorige Volg/Leeg Thesaurus Commando Opzoeken PASSAGIER; GASTRONOMIE; RESTAURANT; PERSONEEL; VAKANTIE; BINNENBEELD; SCHIP; BECKERS LEEN; VRT; LOTTO; RADIOOMROEPSTER; KLANKSTUDIO; UITVINDING; BARBECUE; BETONMOLEN; IBM; RECLAMESPOT rechthebbende : VRT 6 medialab
  • 7. Aha - The Search Engine! 7 medialab
  • 8. Issues – Catch-22 -> Automated processing of information is a key discriminator, but it requires correct and structured metadata -> “Annotation” of rich media requires semantic awareness and interpretation, and thus it is at best an approximation -> Product Engineering is the source of structured and meaningful information, but creative staff are not susceptible to technology 8 medialab
  • 9. Objectives - Proof of Concept • One Set of Numbers(!) • Model Driven Development • Computer Assisted Manufacturing • Unsupervised Feature Extraction • Efficient Search and Retrieval ! Develop an extensible data-model and a consistent application framework, accessible via an intuitive user-interface (! Digitizing analogue and disintegrated information flows) 9 medialab
  • 10. Milestone 1 – Search Engine 10 medialab
  • 11. Milestone 1 – Search Engine ! Search federation by system integration Search Client ! Facetted search (Custom Development) ! Integrated application of keywords ! Intuitive and structured presentation of results ! Direct access to audiovisual material Legacy Video Library (Basisplus) <NewsML-G2> Raw Material (EBU Superpop) Media Asset Search Engine Management System (Lucene/SOLR) (Ardome) Actual news items (Ardome) 11 medialab
  • 12. Shot Segmentation and Scene Recognition 12 medialab
  • 13. Character Recognition 13 medialab
  • 14. Video copy detection ! Identify dupplicates ! Generation tracking ! Grouping of search results ! Intellectual Property Protection 14 medialab
  • 15. Milestone 2 – Feature Extraction ! Time-coded properties and indexing allow random access to material fragments: ! Shot segmentation and Keyframe extraction ! Subtitle processing and Speech recognition ! Taxonomy-driven topic detection ! Face recognition ! Scene recognition ! Copy detection Legacy Video Library (Basisplus) <NewsML-G2> Raw Material Media Asset (EBU Superpop) Management Asset Media Search Engine Management System (Lucene/SOLR) (Ardome)(Ardome) Actual news items (Ardome) Face Detection Shot Topic Segmentation Detection Media Speech 15 medialab Production Recognition
  • 16. Work in Process (due Q4 2008) ! Multi-lingual ! Access control and Intellectual Property Protection ! Audio segmentation and classification ! Music transcription ! Fractal-based visual indexing ! … Media 16 medialab Production
  • 17. Conclusion ! Enterprise search – structured metadata, limited number of libraries, limited number of records per library, dependencies between objects ! Intelligent search federation is aware of the media production process - scripts, webpages, subtitles and formal annotation may represent the same editorial object ! Random access to audiovisual material requires an index is based on timecode and not « wordposition in a document » ! Onthology-driven application logic is essential to create semantic awareness, i.e. resolving synonyms and disambiguation of homonyms ! The perfect search engine is not for sale yet and required from the ground up design and development. 17 medialab
  • 18. Future Work - From « Metadata » to CAD/CAM ? 18 medialab
  • 19. Future Work - From « Metadata » to CAD/CAM ? 19 medialab
  • 20. ! http://medialab.vrt.be/pisa ! http://projects.ibbt.be/pisa ! Maarten.verwaest@vrt.be 20 medialab