SLIDE 1
APIDIS overview
Public slides, 30/01/2008
- Prof. C. De Vleeschouwer – UCL
APIDIS overview Prof. C. De Vleeschouwer UCL Public slides, - - PowerPoint PPT Presentation
APIDIS overview Prof. C. De Vleeschouwer UCL Public slides, - - PowerPoint PPT Presentation
APIDIS overview Prof. C. De Vleeschouwer UCL Public slides, 30/01/2008 Partners O Universit catholique de Louvain, Belgium O Queen Mary University London, UK O Ecole Polytechnique Federale de Lausanne, Switzerland O Fundaci
SLIDE 2
SLIDE 3
APIDIS vision & goal
O Cost-efficient, and high resolution sensors. O Diversity and personalization of media access. → Need to link content acquisition and content consumers. O APIDIS objectives:
- Autonomous acquisition and production of content.
- Personalized summarization of events.
- Interactive browsing/remixing solutions.
SLIDE 4
APIDIS vision & goal
SLIDE 5
APIDIS vision & goal
SLIDE 6
WP structure
WP7 : Integration and validation
Videosurveillance Sport event Personalized summarization Interactive access Autonomous production Two application domains Three action lines
WP1 : Management WP2 : Requirements and specifications WP8 : Dissemination and exploitation WP3 : Sensing network deployment WP4 : Distributed feature extraction WP5 : Scene understanding WP6 : Production and distribution
SLIDE 7
Proof of concept trials
O Automatic and personalized summarization of a video sequence, knowing salient segments. O Generation of high resolution images in any viewing direction based on an array of omnicams. O Distributed feature extraction and analysis for camera view selection.
SLIDE 8
Final demos
O Sharing and remixing of content through intelligent browsing of manually pre-annotated content
- for a production room,
- using raw initial content exploited by local TV.
O Interactive and semantically-driven access to video surveillance content
- for operator or control rooms,
- using indoor/outdoor site surveillance content.
O Automatic generation of personalized summaries of content captured by distributed sensors
- for Internet portals,
- using autonomous distributed sensing.
SLIDE 9
Test-bed architecture
MJPEG video Off-line analysis Annotations
Generic :
time, activity measures..
Consensual User dep.
Scene dependent Autonomous summarization using:
- Interest associated to content
segments,
- Context: user requirements,
targeted platform, interactive process or not.
Browsing facilities GUI Interest computation using:
- Annotations,
- Context: scene semantics,
narration rules, and user interest.
Surveillance & Production room automatic summarization
SLIDE 10
Role of partners
Storage of representative samples and manual annotation of their salient segments. ACIC D 3.2 and 5.1 Distributed audio- visual features extraction and tracking. QMUL D 4.2, 4.3 and 4.4 Event detection and video segment relevance UCL D 5.2 Camera view and display parameters relevance UCL D 5.3 Test-bed for personalized access to multi-view and semantically- augmented content ACIC D 6.1 Test-bed for autonomous creation
- f multi-view and semantically-
augmented content. ACIC D 6.1 Converting
- mni-directional
images into planar ones. EPFL D 3.3 Semantically- meaningful summarization
- f content.
UCL D 6.2 Interactive access to intelligent content. BM D 6.4 Distributed sensing. MP D 3.1 and 4.1
Software for automatic acquisition of content intelligence* Software for intelligent* content manipulation
* ‘Intelligence’ refers to knowledge about the semantic relevance of content segments, i.e. to salient segments definition.
User-centered requirements + assessment
BM D 2.1, 2.2, 2.3 D 6.3
Proof-of-concept trials and final demos
MP D 7.1, 7.2, 7.3
SLIDE 11
Time table
SLIDE 12
Test-bed incremental development
SLIDE 13