Automatic conversion of traffic accident reports into 3D animations
Author
Editor
- Tomas Akenine-Möller
Summary, in English
This paper describes a system that automatically converts narratives into 3D scenes. The texts, written in Swedish, describe road accidents. One of the key features of the program is that it animates the generated scene using temporal relations between the events. We believe that this system is the first text-to-scene converter that is not restricted to invented narratives.
The system consists of three modules: natural language interpretation based on information extraction (IE) methods, a planning module that produces a geometric description of the accident, and finally a visualization module that uses Java3D to render the geometric description as animated graphics.
We performed a small user study to evaluate the quality of the visualization. The results validate our choice of methods, and since this is the first evaluation of a text-to-scene conversion system, they also provide a baseline for further studies.
The system consists of three modules: natural language interpretation based on information extraction (IE) methods, a planning module that produces a geometric description of the accident, and finally a visualization module that uses Java3D to render the geometric description as animated graphics.
We performed a small user study to evaluate the quality of the visualization. The results validate our choice of methods, and since this is the first evaluation of a text-to-scene conversion system, they also provide a baseline for further studies.
Publishing year
2005
Language
English
Pages
25-29
Publication/Series
Proceedings of SIGRAD-05
Document type
Conference paper
Topic
- Computer Science
Keywords
- Natural language processing
- computer graphics
- automatic illustration
Conference name
SIGRAD 2005
Conference date
2005-11-23 - 2005-11-24
Conference place
Lund, Sweden
Status
Published