This paper describes Webber, a networked virtual environment system, which provides a realistic three dimensional cyberspace for users to navigate freely. Webber is a prototype implementation of DOOViE (Distributed Object-Oriented Virtual Enviromnent), which is a framework for constructing a multi-user virtual environment over the network. DOOViE has a hierarchical structure using object-oriented paradigm. The high-level components in DOOViE hierarchy are highly independent of each other and thus reusable. They can be distributed over the machines in the network. Webber is aimed at both testing the DOOViE concept and investigating the tradeoff between the computational resources and the communication resources in a distributed system.

Multiscale structures and algorithms that unify the treatment of local and global scene information are of particular importance in image segmentation. Vector quantization, owing to its versatility, has proved to be an effective means of image segmentation. Although vector quantization can be achieved using self-organizing maps with competitive learning, self-organizing maps in their original single-layer structure, are inadequate for image segmentation. A hierarchical self-organizing neural network for image segmentation is presented. The Hierarchical Self-Organizing Map (HSOM) is an extension of the conventional (single-layer) Self-Organizing Map (SOM). The problem of image segmentation is formulated as one of vector quantization and mapped onto the HSOM. By combining the concepts of self-organization and topographic mapping with those of multiscale image segmentation the HSOM alleviates the shortcomings of the conventional SOM in the context of image segmentation.

This paper proposes and describes a hierarchical self-organizing neural network for range image segmentation. The multilayer self-organizing feature map (MLSOFM), which is an extension of the traditional (single-layer) self-organizing feature map (SOFM) is seen to alleviate the shortcomings of the latter in the context of range image segmentation. The problem of range image segmentation is formulated as one of vector quantization and is mapped onto the MLSOFM. The MLSOFM combines the ideas of self-organization and topographic mapping with those of multiscale image segmentation. Experimental results using real range images are presented.

A scheme for recognition of three-dimensional objects, using the vertex-pair feature, is described. Coarse-to-fine histogramming on an n-dimensional grid is used to compute the best affine transformation between the model and the scene. Transform equations are derived and performance results for an implementation on a fine-grained data parallel machine, the Connection Machine, are presented.

An O(N3K) time algorithm for searching matches of a template of size K in an image of size N is given. It uses bounding regions and the Soviet Ellipsoid Algorithm [1]. It will work under moderately heavy shift noise.