Fujitsu Corporation

Shinya Hosogi

Yoshiharu Maeda

Kuniharu Takayama

Masahiro Matsuoka

Hirohisa Naito

Hiroaki Okamoto

Minoru Sekiguchi

Susumu Kawakami

Kazuo Misue

Takeshi Koshiba

Kozo Sugiyama

Hiroyuki Kano

Etienne Burdet

There is disclosed a technology of measuring three-dimensional geometric information on a plane and position information on a point from an image such as the optical flow pattern and a stereo image. It is to determine an azimuth of a measuring plane and/or a superposing time in which the measuring plane is superposed on a predetermined observation point, using a compound ratio &lcub;p p p p &rcub;, which is determined by four positions p , p , p , p of a measuring point, where p and p denote measuring positions at mutually different two measuring times on an arbitrary measuring point appearing on an image obtained through viewing a predetermined measurement space from a predetermined observation point inside the measurement space, respectively, p denotes a position of the measuring point after an infinite time elapses, and p denotes a position of the measuring point at a superposing time in which a measuring plane including the measuring point is superposed on the observation point in the moving continuous state.

Image measurement method, image measurement apparatus and image measurement program storage medium

A data converting device collects time series movement data by measuring a movement of a living thing, encodes the movement data, and stores the encoded data in a storage device. Next, the data converting device generates new encoded data by reading and editing the encoded data. The data converting device then restores the movement data from the encoded data, and reproduces the movement of a virtual character on a display device based on the restored data.

Data converting device for encoding and editing time series data and method thereof

In the dialog interface apparatus of the present invention, input speech is converted to an input semantic representation by a speech recognition unit, and a dialog management unit outputs an output semantic representation that corresponds to the input semantic representation, based on the input semantic representation obtained by the speech recognition unit. Having received the output semantic representation from the dialog management unit, a speech synthesis unit converts the output semantic representation to output speech identifying a specific dialog target and outputs the output speech. Further, the dialog management unit outputs to an innate operation execution unit an innate operation command that corresponds to the input semantic representation. The innate operation execution unit receives the innate operation command from the dialog management unit and executes an operation corresponding to the innate operation command.

Dialog interface system

The present invention relates to a neural network system for determining a position of a mobile object such as a robot, automobile, etc., which comprises a return information processing unit for generating return information corresponding to a relative position of the mobile object from the origin in a move space according to first sensor signal from the first sensor; a sense information processing unit for generating sense information corresponding to an environment state surrounding the moblie object at the relative position according to a second sensor signal from the second sensor; and an information integrating unit for inferring return information corresponding to sense information output from the sense information processing unit after learning a correlation between the return information and the sense information, and integrating the two items of information.

Learning type position determining device

A system identifying device precisely represents as a mathematical model the features of a system such as a robot manipulator, various industrial plants, etc., and can be operated as hardware by identifying an object system over a neural network, thereby successfully identifying a non-linear system as well as a linear system. Furthermore, an adaptive control device can perform an online learning by using the identifying device to obtain a teaching signal to be used in operating the identifying device in an adaptive control device.

System identifying device and adaptive learning control device

Using a writing implement model defined in the O-XYZ coordinate system a character or graphic form is generated on a writing plane model (O-XY plane) defined in the O-XYZ coordinate system. A control polygon for a character or graphical form to be generated is designed in advance in the O-XYZ coordinate system and a smooth writing motion model is generated using local basis functions that are weighted by the coordinate values of the respective vertices of that control polygon. The position component of the writing motion model represents variations in the position of a representative point of the writing implement model in the O-XYZ coordinate system with respect to time, and the posture component of the writing motion model represents time-variations of its inclination in the O-XYZ coordinate system with respect to the O-XYZ coordinate system. The writing implement model and the writing plane model intersect at a time, thereby forming a character segment. If character segments are generated at regular intervals between the start point and the end point of the writing motion, then the entire image of a character or graphic form will be obtained automatically.

Growing community of inventors

Kawasaki, Japan

Shinya Hosogi