1 / 18

aceMedia Personal content management in a mobile environment

aceMedia Personal content management in a mobile environment. Jonathan Teh Motorola Labs. The Figures. FP6 Integrated Project 9 countries 45 staff (approx.) 6 industrial partners 4 large 2 SMEs 7 academic partners 4 Universities 3 National Research Centres

orli
Download Presentation

aceMedia Personal content management in a mobile environment

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. aceMediaPersonal content management in a mobile environment Jonathan TehMotorola Labs

  2. The Figures • FP6 Integrated Project • 9 countries • 45 staff (approx.) • 6 industrial partners • 4 large • 2 SMEs • 7 academic partners • 4 Universities • 3 National Research Centres • Co-ordinator : Motorola Ltd • Started : 1 Jan 2004 • Duration : 4 years • Total Budget: €17M 2

  3. Transmission Storage Content Creation Content Analysis & Annotation Intelligent Search & Presentation • aceMedia will implement a full content value chain which will enable content and knowledge creation, update, transmission, and manipulation & exploitation (through advanced search and retrieval and intelligent content behaviour) aceMedia vision • aceMedia aims to discover and exploit knowledge inherent in multimedia content, making it more relevant for the user and automating annotation. 3

  4. The Autonomous Content Entity Programmable layer, enabling the ACE to be self-sufficient, self-organizing, self-analysing Intelligence Layer Knowledge-based Automatic Semantic analysis and annotation using ontologies and Semantic Web technologies. Metadata Layer Content Layer ACE Scalable content for reuse in different devices, different situations and user needs. 4

  5. ACE lifecycle Knowledge-Assisted Analysis aceToolbox Person Detection Face Detection Natural Language Processing Multimedia Indexing Self-governance NLP Visual Search Relevance Feedback Personalised Retrieval Cross-Media Engine Content delivery tools Content self-organization 5

  6. Empty ACE creation • Digital content is created and imported into an aceMedia device. • ACE content layer is created • Scalable content through aceMedia SVC and JPEG2000 • Provide support for transmission across different networks and rendering on different devices • ACE intelligent layer possibly defined at ACE creation • Personalising the ACE (presentation, sharing rules, visibility), making it self-organising, … Intelligence Layer Metadata Layer Content Layer ACE 6

  7. User, Terminal & Network Profiles ACE CME Adapted ACE ACE transmission and presentation • ACEs are transmitted through heterogeneous networks and presented on aceMedia devices • aceMedia Cross-Media Engine (CME) acts as a processing node to: • Select the appropriate parameters and adaptation modality based on user, device and network profiles • Select the appropriate available content adaptation tool • Configure and manage that tool to create the adapted content • Both content and metadata are scalable 7

  8. ACE pro-activeness • The ACE intelligent layer • Provides the ACE with pro-active behaviour • As opposed to passive, static content • Takes functionality together with the content • Allows complex personalization features • Allows better exploitation of the knowledge attached to content: ACE metadata layer • Can make use of complex content analysis • But… • Has to be executed in a sandbox • Risk of malicious code • Challenging in constrained devices 8

  9. Knowledge Infrastructure Content Management Content Delivery Tools Content Analysis Cross-Media Engine Content Engineering Wavelet based scalable video codec aceMedia structure 9

  10. Multimedia Reasoning Person and Face Detection & Recognition Knowledge Infrastructure Content Management Region Labelling Content Analysis Natural Language Processing Content Classification Content Engineering Low-level Features aceMedia structure 10

  11. Content Privacy Mgmt Knowledge Infrastructure Content Management Self-Organization Content Analysis Personalized Browsing Content Engineering Intelligent Search and Retrieval aceMedia structure 11

  12. ACE Repository Software Architecture aceMedia Application Other aceMedia applications over the same aceFramework … aceManager ACE Intelligence Exec. Env. aceNetwork Layer AMRegistry Configuration Storage aceFramework Java VM OS 12

  13. Platforms • aceMedia system supports multiple platforms • Framework • Implemented in Java for portability • Linux on all platforms • JNI used where performance is necessary • OSGi for dynamically loadable modules • Content engineering • Scalable codecs to adapt to different networks and devices • JXTA network layer for content delivery • Content analysis • Remote invocation of modules to perform analysis on a different device • Content management • Self-governance to ensure access rights are enforced • Application • Multiple UIs designed to take into account different form factors, display sizes and input devices 13

  14. User Interface • Prototyped on an A780 Browsing collections Creating a collection Browsing a collection 14

  15. User Interface (2) Edit annotations (detailed) Search word and image 15

  16. Conclusion • Entering the 4th and final year of the project • Implemented software modules for content engineering, analysis and management • Software running on multiple platforms • Performed user studies on multiple platforms 16

  17. Backup slides 17

  18. NLP processes manual annotations If rich enough, then automatic selection of domain ontology Visual Content Detector Manual Annotations Person and Face detection and recognition Content is classified: indoor / outdoor natural / man-made Standing persons and faces detected. Learned faces recognized. Knowledge-Assisted Analysis Ambiguities removed. Regions merged. Final consistent semantic annotation Regions are labelled with concepts from the domain ontology Multimedia Reasoning Empty Manual Annotations Automatic Semantic Annotations ACE update - typical annotation process aceMedia content analysis ACE ACE 18

More Related