Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on

Describes and compares five techniques for vision-based tracking of a subject's head in front of a desktop PC. These algorithms are based on color, motion magnitude, background subtraction, face detection, and a probabilistic fusion of the first three algorithms. Head tracking is used to determine the subject's position with respect to the monitor noninvasively. This information is used, in turn, ... View full abstract»

Deals with spatio-temporal indexing methods for moving objects. Spatio-temporal indexing gives a basis for a data management structure for the efficient searching of large-scale spatio-temporal data. In this paper, two types of indexing methods are proposed for managing spatio-temporal data for moving objects. Both methods are evaluated by computer simulation and the merits and demerits of both me... View full abstract»

Presents a relief modeling system in a virtual space. Since relief-like objects are basically shaved from one direction, we describe the objects as 2.5-dimensional shapes by using polygon-meshed height maps. This data description is simple, so that the objects can be easily modified. Our system offers a user interface which is similar to real relief modeling. Users can engrave various ditches on o... View full abstract»

With the rapid expansion of virtual environments in research, entertainment, art and industry, the need for a larger variety of image sources for the construction of these environments has become an important issue. Recent computer modeling has become increasingly sophisticated, and digital effects for movies such as "Titanic", "Star Wars" and other Hollywood productions are not short on convincin... View full abstract»

The explosive use of the Internet-from the advent of the World Wide Web (WWW)-has brought about a lot of Internet applications. The current static and document-oriented WWW, however, is making it difficult to interact with other people through the Internet. Consequently, there have been many efforts to provide humans with ways to interact and collaborate. For our part, we have developed PVET (Pers... View full abstract»

The search for suitable data input for a description of mechanical assemblies (MAs) and for a standardized method of information exchange are worldwide problems. The separate design tasks (preparation of the specification, assembly and parts' drafting, assembly planning, dimensional tolerance analysis, etc.) are usually solved without an appropriate united medium model of a MA. For this objective,... View full abstract»

Presents an overview of our efforts on mixed reality. These efforts span two aspects: how to create models of virtual objects and how to integrate such virtual objects with real scenes. For model creation, we have developed two methods (the model-based and eigen-texture rendering methods), both of which automatically create models by observing real objects. For the integration of a virtual object ... View full abstract»

Introduces case studies of mixing real and virtual worlds in our "mixed reality" (MR) project. MR is a part of virtual reality in the broader sense, but it treats physical space as well as the virtual space generated by computers. We use the term "mixed reality" instead of the more often used "augmented reality" (AR) because the merging or integration of the real and virtual worlds should not be c... View full abstract»

Proposes seamless view-mode switching, a novel technique for supporting spatial collaboration that integrates a shared virtual environment (SVE) and a shared augmented environment (SAE) in a natural way. The technique uses two view modes: a see-through mode and a blind mode, corresponding to an SAE and an SVE, respectively. In the initial state, the view mode is the see-through one. Whenever a use... View full abstract»

The multi-user networked virtual world system "High-Quality InterSpace" (HiQIS) is described. HiQIS's main purpose is to enhance the user's communication activities in InterSpace, which is a multi-user 3D shared virtual space system. In InterSpace, users can communicate with each other using their avatars with video facial images and their own voices. HiQIS improves the avatar's appearance and the... View full abstract»

Recently computers have enabled users to walk through cyberspace using interactive virtual reality techniques. An avatar in cyberspace can allow a virtual face-to-face communication environment. The article realizes an avatar which has a real face in cyberspace to construct a multi-user communication system by voice transmission through a network. A voice from a microphone is transmitted and analy... View full abstract»

ATR Media Integration and Communications Research Laboratories (ATR MIC) are aiming at realizing communication environments in which remotely located people can communicate with each other via a virtual scene. Virtual metamorphosis systems are possible applications of such virtual communication environments. In the virtual metamorphosis system, people can change their forms into any other form in ... View full abstract»

The Distributed Virtual Environment (DVE) is expected as a promising communication technology in the future. And, the productivity of DVE systems is an important subject for the progress of DVE. We propose a novel method for expanding DVE more consistently, and develop a prototype DVE system which we call the EX-DVE system. EX-DVE is a kind of DVE where users can easily add virtual objects into th... View full abstract»

One goal in the development of distributed virtual environments (DVEs) is to create a system such that users are unaware of the distribution-the distribution should be transparent. The paper begins by discussing the general issues in DVEs that might make this possible, and a system that allows some level of distribution transparency is described. The system described suffers from effects of incons... View full abstract»

While the demand for 3D technologies is growing rapidly, there are some fundamental problems remaining unresolved, such as a way to intuitively create 3D object data in a virtual environment. This paper proposes a new method for creating 3D objects using bi-manual gestures. To realize an easy-to-use yet powerful modeling capability, we designed a framework defining a dozen primitive hand actions t... View full abstract»

A collaborative scientific visualization environment was constructed by connecting the CABIN immersive multi-screen display system to several immersive projection displays and to supercomputers via a broadband network. In this environment, users in remote places are able to discuss the displayed phenomena while looking at the same data. In particular, a video avatar method was developed to realize... View full abstract»

Mixed reality (MR) is a technique which can combine a virtual environment and a real environment without making users feel that anything is unnatural. We propose a method using a see-through head mounted display (STHMD) to improve the precision of depth perception using tactile feedback. The visual accuracy of depth perception was measured when virtual objects were displayed through a STHMD. Subje... View full abstract»

Describes a new approach for building a photorealistic virtual world based on the real world. Using an image capturing system mounted on a vehicle, we have assembled a vast image database with global position and orientation information. However, if we store all the images taken from various users' viewpoints, we might exhaust the resources. Thus, it is important to generate novel images from fini... View full abstract»

Since membership functions and fuzzy control rules are interdependent in designing a fuzzy logic controller (FLC), a GA-based approach is proposed for simultaneous design of these two components. With triangular membership functions, the left and right widths of these functions, the locations of their peaks, and the output fuzzy set corresponding to every possible combination of input fuzzy sets a... View full abstract»

A fuzzy-neural network needs to be trained through a learning process, so that suitable membership functions and weightings can be obtained. However, most neural networks are only simulated by computer software, which are not practical for real applications. It is therefore our objective to design an integrated circuit system based on a DSP processor with powerful arithmetical capabilities and fas... View full abstract»

We propose support vector machines (SVM) to improve the simplified fuzzy inference system for the fuzzy neural network. Firstly, we apply SVM to determine the number of simplified fuzzy inference system rules. Because training a SVM is equivalent to solving a linear constrained quadratic programming problem under a fixed structure of SVM, we can easily determine the number of simplified fuzzy infe... View full abstract»

The purpose of this research is to develop methodology for generating large and complex neural networks. Especially, in this case, we adopt the methods to the organizational task in a multi-agent system. We propose the incremental evolution of weight modifiers for generating neural networks based on the GA. In this method, a chromosome contains only the instructions for making and modifying the we... View full abstract»

We propose an evolutionary self-organizing neural network for blind deconvolution. The evolutionary self-organizing neural network has two steps of learning: one is the self-organizing learning, the other focuses on a genetic algorithm. The self-organizing learning function maximizes the Gibbs distribution of the information distance. An improvement by the genetic algorithm is made between two ite... View full abstract»

Classification of terrain cover using polarimetric radar is an area of considerable interest and research. This paper describes the application of neural network approach to the classification of a fully polarimetric SAR image. The structure and connection weights of the network are decided based on the cascade correlation algorithm. The procedures are performed by interleaving the minimization of... View full abstract»