Part-Based Annotation of Virtual 3D Shapes

In the latest years, distributed virtual worlds populated by static and dynamic 3D shapes have grown significantly, and the need to model and process them effectively has become a critical issue. The introduction of semantic annotations for capturing characteristics and behaviours is foreseen as a fundamental contribution to move from traditional geometric shapes towards self-describing semantic shapes. To this aim, we describe the foundations of a novel system that allows us to perform non-trivial segmentations of 3D surface meshes and to annotate the detected parts through concepts expressed by an ontology. Each part is connected to an instance in a knowledge base, allowing easier retrieval in a semantics-based context. We show how the part-based annotation framework might be used in two scenarios, namely for the creation of avatars in emerging Internet-based virtual worlds and for product design in emanufacturing.