An object oriented design for the visualization of multi-variable data objects

Abstract

This paper presents an object-oriented system design supporting the composition of scientific data visualization techniques based on the definition of hierarchies of typed data objects and tools. Traditional visualization systems focus on creating graphical objects which often cannot be re-used for further processing. Our approach provides objects of different topological dimension to offer a natural way of describing the results of visualization mappings. Serial composition of data extraction tools is allowed, while each intermediate visualization object shares a common description and behavior. Visualization objects can be re-used, facilitating the data exploration process by expanding the available analysis and correlation functions provided. This design offers an open-ended architecture for the development of new visualization techniques. It promotes data and software re-use, eliminates the need for writing special purpose software and reduces processing requirements during interactive visualization sessions.<>