In this paper, we propose to use staying area data toward the estimation of serving time for customers. To classify utterances enables us to estimate conversation types between speakers. However, its performance becomes lower in real environments. We propose a method using area data with sound data to solve this problem. We also propose a method to estimate the conversation types using the decision trees. They were tested with the data recorded in a Japanese restaurant. In the experiment to classify utterances, the proposed method performed better than the method using only sound data. In the experiment to estimate the conversation types, we succeeded to recover 70% of the mis-classified conversations using both of sound and area data.

This paper describes the constructing method of consistent action scene data of CG charactors. The proposed method realizes to construct multiple characters' action scenes by merging one actor's action sequences with keeping time and space consistencies between multiple individually recorded or manually-designed action sequences semi-automatically. This technique is planned as a part of "Mixed Reality Pre-visualizing As Pre-Production Tool in Film-making; MR-PreViz" which can streamline the filmmaking process by overlaying CG action data on the real background image in real time.

This paper describes a novel image-based geometric registration method using visually elegant and robust semi-fiducial markers in mixed reality (MR). Most traditional visual markers stand out against the background, i.e., they can be recognized and identified easily. Here, we try to construct new visual markers for MR registration, which achieve a good balance between visual elegance and robustness. As the first step, we propose "two-tone colored markers". These markers have the following characteristics: 1) color similar to that of the background object, 2) placed at the corners of real objects in an inconspicuous manner. This paper describes the registration method using two- tone colored markers and a few experiments.

By realizing augmented reality on wearable computers, it is possible to overlay annotations on the real world based on the user's current position and orientation. However, it is difficult for the user to understand links between annotations and real objects intuitively when the scene is complicated or many annotations are overlaid at the same time. This work describes a view management method which emphasizes user-viewed real objects and their annotations using 3D models of the real scene. The proposed method highlights the objects viewed by the user. In addition, when the viewed object is occluded by other real objects, the object is complemented by using an image, which is made from 3D models, on the overlaid image.

This paper describes a wearable augmented reality system using positioning infrastructures and a pedometer. To realize augmented reality systems, the position and orientation of user's viewpoint should be obtained in real time. The proposed system measures the orientation of user's viewpoint by an inertial sensor and the user's position using positioning infrastructures in environments and a pedometer. The system specifies the user's position using the position ID received from RFID tags or IrDA markers which are the components of positioning infrastructures. When the user goes away from them, the user's position is alternatively estimated by using a pedometer. We have developed a navigation system using the proposed techniques and have proven the feasibility of the system with experiments.