Ihi Corporation

Ishikawajima-harima Heavy Industries Co., Ltd.

Hajime Banno

Takeshi Takahashi

Toshihiro Hayashi

Shusaku Yamasaki

Masakazu Fujii

Mitsuharu Sonehara

Shuhei Emoto

Kentaro Mizouchi

Makoto Ikarashi

Shinichirou Sonoda

A line segment detection method includes acquiring an image, extracting from the image a straight line that includes a line segment, acquiring a luminance distribution of the straight line, generating a virtual function model that contains a distribution of a foreground and a background of the image by using the luminance distribution, and determining whether luminance values near end points (start point and end point) of the line segment contained in the virtual function model probabilistically belong to the foreground or the background, and estimating end points (start point and end point) in the virtual function model.

Line segment detection method

When correction values are respectively determined for noise components of 'OFFSET COMPONENT OF CCD ELEMENT', 'GRADATION COMPONENT OF BACKGROUND LIGHT' and &#x201c;OFFSET COMPONENT OF OPTICAL SYSTEM&#x201d;, the pixel values including as less of these noise components as possible are evaluated. The evaluated pixel values include a noise component of &#x201c;THERMAL NOISE PLUS READOUT NOISE COMPONENT&#x201d; which is superposed onto the pixel values. With this taken into consideration, a moving object detection method of an embodiment photographs multiple images of a moving object being an observation object with a photographic area fixed, selects the smallest pixel value in each group of corresponding pixels across the images from image signals representing the images, evaluates image signals including as less of the four noise components as possible by using the smallest pixel value as the correction value for the four noise components.

Moving object detection method

A moving object detection method according to an embodiment includes evaluating an average value, instead of a median value, of pixel values at the same pixel positions across multiple superposed images. A threshold value obtained by multiplying the average value by a predetermined number is employed to distinguish space debris from an object which emits light at a higher luminance than the space debris. In order to detect the space debris accurately, an average value of the pixel values that are equal to or less than the threshold is employed as an evaluation value for the space debris detection.

A moving object detection method according to an embodiment performs a stacking process step of: dividing captured images into p groups each including m successive images; and for each group, applying a stacking method to the m images. Subsequently, for each group, the method extracts a candidate for space debris based on an evaluation value for space debris detection, which is obtained from pixel values at the same pixel positions overlapping one another across the m images superposed one another. Thereafter, the method judges whether the extracted candidate for the space debris in each group is chosen as a final candidate for the space debris based on the coincidence or proximity in terms of the movement direction and the moving velocity.

(A) One or both of an object and a robot are measured by measuring units to acquire sensor information. (B) The internal state of one or both of the object and the robot is predicted and updated by a state estimation unit on the basis of the sensor information. (C) The internal state is stored by a data storage unit. (D) The robot is controlled by a robot control unit. At (B), the internal state is updated by the state estimation unit at an arbitrary timing that is independent of the control cycle of the robot. At (D), a prediction value necessary for controlling the robot is calculated by the robot control unit at a control cycle on the basis of the latest internal state stored in the data storage unit.

Motion prediction control device and method

By adopting a workpiece transfer apparatus, which grips a workpiece by use of a predetermined grip device and transfers the workpiece between press apparatuses each of which drives a die, including a transfer control device for controlling a position of the grip device based on a resultant target value obtained by combining a die position of a press apparatus located on an upstream side of a workpiece transfer direction (an upstream side die position) and a die position of a press apparatus located on a downstream side of a workpiece transfer direction (a downstream side die position), in which the transfer control device sets a resultant target value so that the grip device moves smoothly, it becomes possible to suppress vibration in a workpiece transfer apparatus in a press line.

Workpiece transfer apparatus, control method for workpiece transfer apparatus, and press line

There are provided an image compression device, method, and program, a compression code data encoding device, method, and program, and a decoding device, method, and program. The image compression device includes: means for dividing the entire image into blocks, calculating an inclined plane or an outer edge inclined plane for calculating a parameter specifying the inclined plane or the outer edge inclined plane for approximating the respective blocks from the block pixel values, calculating an error amount or a difference value to calculate a difference between the inclined plane or the outer edge inclined plane and the respective pixel values, and calculating an encoding correction amount of each block; and encoding portion for reversibly encoding the parameter specifying the inclined plane or the outer edge inclined plane. The encoding device includes synthesis portion for judging a change amount of generation probability contained in the data to be compressed and obtained in time series, generating difference probability data including a generation probability of data having a large generation probability, and synthesizing the generated difference probability data with the compression/encoding data.

Image compression device, image compression method, image compression program, compression encoding method, compression encoding device, compression encoding program, decoding method, decoding device, and decoding program

Growing community of inventors

Tokyo, Japan

Hajime Banno