Tomoji Toriyama

TL;DR: In this paper, the authors proposed a visual volume intersection method to generate a 3D model of an object by using the residual projection point acquired by projecting one voxel to a processing object image photographed from one camera viewpoint.

TL;DR: In this article, an action identification system consisting of a server 12, which receives acceleration data transmitted from sensor devices 16 and stores the data in a sensor DB 20 is presented, where each sensor is provided with an acceleration sensor, wherein acceleration data from the acceleration sensor is transmitted to the server 12.

TL;DR: This work proposes a robust method to detect foreground regions from colour video sequences using a generalised Gaussian family model and multiple thresholds and shows that the proposed algorithm works better than conventional approaches in various environments.

TL;DR: In this article, a server selects a nurse to whom the information should be presented, and determines whether or not the information is ready to be presented to the selected nurse under the consideration of the circumstances of the nurse at that time and the content (urgency level) of the information.