TU Darmstadt / ULB / TUbiblio

Generative Object Definition and Semantic Recognition

Ullrich, Torsten and Fellner, Dieter W. (2011):
Generative Object Definition and Semantic Recognition.
In: Eurographics Workshop and Symposia Proceedings Series, pp. 1-8, Eurographics Association, Goslar, Eurographics 2011 Workshop on 3D Object Retrieval, DOI: 10.2312/3DOR/3DOR11/001-008,
[Conference or Workshop Item]

Abstract

"What is the difference between a cup and a door?" These kinds of questions have to be answered in the context of digital libraries. This semantic information, which describes an object on a high, abstract level, is needed in order to provide digital library services such as indexing, mark-up and retrieval. In this paper we present a new approach to encode and to extract such semantic information. We use generative modelling techniques to describe a class of objects: each class is represented by one algorithm; and each object is one set of high-level parameters, which reproduces the object if passed to the algorithm. Furthermore, the algorithm is annotated with semantic information, i.e. a human-readable description of the object class it represents. We use such an object description to recognize objects in real-world data e.g. laser scans. Using an algorithmic object description, we are able to identify 3D subparts, which can be described and generated by the algorithm. Furthermore, we can determine the needed input parameters. In this way, we can classify objects, recognize them semantically and we can determine their parameters (cup's height, radius, etc.).

Item Type: Conference or Workshop Item
Erschienen: 2011
Creators: Ullrich, Torsten and Fellner, Dieter W.
Title: Generative Object Definition and Semantic Recognition
Language: English
Abstract:

"What is the difference between a cup and a door?" These kinds of questions have to be answered in the context of digital libraries. This semantic information, which describes an object on a high, abstract level, is needed in order to provide digital library services such as indexing, mark-up and retrieval. In this paper we present a new approach to encode and to extract such semantic information. We use generative modelling techniques to describe a class of objects: each class is represented by one algorithm; and each object is one set of high-level parameters, which reproduces the object if passed to the algorithm. Furthermore, the algorithm is annotated with semantic information, i.e. a human-readable description of the object class it represents. We use such an object description to recognize objects in real-world data e.g. laser scans. Using an algorithmic object description, we are able to identify 3D subparts, which can be described and generated by the algorithm. Furthermore, we can determine the needed input parameters. In this way, we can classify objects, recognize them semantically and we can determine their parameters (cup's height, radius, etc.).

Series Name: Eurographics Workshop and Symposia Proceedings Series
Publisher: Eurographics Association, Goslar
Uncontrolled Keywords: Forschungsgruppe Semantic Models, Immersive Systems (SMIS), Business Field: Digital society, Business Field: Virtual engineering, Business Field: Visual decision support, Research Area: Generalized digital documents, Research Area: Semantics in the modeling process, Generative modeling, Object classes, Shape semantics, Digital libraries
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Event Title: Eurographics 2011 Workshop on 3D Object Retrieval
Date Deposited: 12 Nov 2018 11:16
DOI: 10.2312/3DOR/3DOR11/001-008
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details