ݺߣ

ݺߣShare a Scribd company logo

A semantic-based framework for managing, searching and retrieving 3D resources - Part1

•
•
Marios Pitikakis
Marios Pitikakis

A semantic-based framework for managing, searching and retrieving 3D resources - Part 1. Presentation at VSMM09 Workshop on 3D Knowledge Technologies for Cultural Heritage Applications.

1 of 15
A semantic-based framework for managing, searching and retrieving 3D resources Marios Pitikakis, CERETETH Chiara Catalano, IMATI-CNR www.cereteth.gr
What’s needed for sharing? Feature extraction Indexing Metadata While addressed successfully for text and 2D content, the management of semantic 3D shapes is still in its infancy Content-based analysis and retrieval
What’s semantics? Knowledge related to the geometry of the 3D shape Knowledge related to the application domain in which the object is manipulated Knowledge related to the meaning of the object represented by the 3D model
To turn 3D shapes in semantic shapes CG KT o 3D shape analysis & o metadata and standards for segmentation 3D annotation o 3D object comparison & o ontologies (broad & narrow classification domains) o 3D scene understanding o formalization of workflows, o smart 3D modelling tools functionalities o 3D mark-up  3D models representing not only shape but also semantics  3D media annotation tools (manual, automatic)  intelligent virtual environments
Adding semantics to geometry We have to extract and associate knowledge to digital content Shape analysis: extracts implicit info coded into the geometry Numerical values (e.g. volume, area, spatial distribution, curvature) Shape descriptors (structuring the shape) Segmentation geometry structure semantics
Semantic-driven segmentations They captures semantically relevant features automatically what is relevant in the cultural heritage context? IMATI segmentation methods for triangle meshes: Fitting primitives Reeb Graphs Tailor Plumber They extract specific kind of knowledge suitable also for virtual heritage
IMATI segmentation methods
Adding semantics to geometry We have to extract and associate knowledge to digital content and its subparts Shape Annotation: it documents the shape with contextual knowledge either manually or automatically geometry structure semantics
AIM@SHAPE approach Ontology Metadata Geometry
ShapeAnnotator: general framework Shape A surface mesh Abstracted Shape Shape A segmented mesh CG Tools Segmentation Plug-ins Annotator Domain An OWL ontology Instance Instance Expert Knowledge Base
ShapeAnnotator: multi-segmentation Pick the interesting features from different shape segmentations (b) Morse-based (c) Plumber (d) Fitting primitives
The ShapeAnnotator: ontology browser
The ShapeAnnotator: knowledge base
CH example….
AIM@SHAPE Digital Shape Workbench Components Ontologies Shape repository Tool repository Pubblications Glossary Browsing Search By keyword By semantics By geometry (DEMO)

More Related Content

A semantic-based framework for managing, searching and retrieving 3D resources - Part1

  • 1. A semantic-based framework for managing, searching and retrieving 3D resources Marios Pitikakis, CERETETH Chiara Catalano, IMATI-CNR www.cereteth.gr
  • 2. What’s needed for sharing? Feature extraction Indexing Metadata While addressed successfully for text and 2D content, the management of semantic 3D shapes is still in its infancy Content-based analysis and retrieval
  • 3. What’s semantics? Knowledge related to the geometry of the 3D shape Knowledge related to the application domain in which the object is manipulated Knowledge related to the meaning of the object represented by the 3D model
  • 4. To turn 3D shapes in semantic shapes CG KT o 3D shape analysis & o metadata and standards for segmentation 3D annotation o 3D object comparison & o ontologies (broad & narrow classification domains) o 3D scene understanding o formalization of workflows, o smart 3D modelling tools functionalities o 3D mark-up  3D models representing not only shape but also semantics  3D media annotation tools (manual, automatic)  intelligent virtual environments
  • 5. Adding semantics to geometry We have to extract and associate knowledge to digital content Shape analysis: extracts implicit info coded into the geometry Numerical values (e.g. volume, area, spatial distribution, curvature) Shape descriptors (structuring the shape) Segmentation geometry structure semantics
  • 6. Semantic-driven segmentations They captures semantically relevant features automatically what is relevant in the cultural heritage context? IMATI segmentation methods for triangle meshes: Fitting primitives Reeb Graphs Tailor Plumber They extract specific kind of knowledge suitable also for virtual heritage
  • 8. Adding semantics to geometry We have to extract and associate knowledge to digital content and its subparts Shape Annotation: it documents the shape with contextual knowledge either manually or automatically geometry structure semantics
  • 9. AIM@SHAPE approach Ontology Metadata Geometry
  • 10. ShapeAnnotator: general framework Shape A surface mesh Abstracted Shape Shape A segmented mesh CG Tools Segmentation Plug-ins Annotator Domain An OWL ontology Instance Instance Expert Knowledge Base
  • 11. ShapeAnnotator: multi-segmentation Pick the interesting features from different shape segmentations (b) Morse-based (c) Plumber (d) Fitting primitives
  • 15. AIM@SHAPE Digital Shape Workbench Components Ontologies Shape repository Tool repository Pubblications Glossary Browsing Search By keyword By semantics By geometry (DEMO)