Abstract: In a pose estimation for estimating the pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating a pose, a data processing device: extracts pose parameters from a binarized image; identifies a combination of pose parameters for which the number of cross surfaces of parameter surfaces that accord with surface parameter formulas, which are numerical formulas for expressing a reference surface, is a maximum; finds a slope weighting for each of cross pixels, which are pixels on each candidate surface and which are pixels within a prescribed range, that is identified based on the angles of the tangent plane at the cross pixel and based on planes formed by each of the axes of parameter space; and identifies the significant candidate surface for which a number, which is the sum of slope weightings, is a maximum, as the actual surface that is the reference surface that actually exists in the image.

Abstract: In a pose estimation for estimating the pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating a pose, a data processing device: extracts pose parameters from a binarized image; identifies a combination of pose parameters for which the number of cross surfaces of parameter surfaces that accord with surface parameter formulas, which are numerical formulas for expressing a reference surface, is a maximum; finds a slope weighting for each of cross pixels, which are pixels on each candidate surface and which are pixels within a prescribed range, that is identified based on the angles of the tangent plane at the cross pixel and based on planes formed by each of the axes of parameter space; and identifies the significant candidate surface for which a number, which is the sum of slope weightings, is a maximum, as the actual surface that is the reference surface that actually exists in the image.

Abstract: In a pose estimation for estimating the pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating a pose, a data processing device: extracts pose parameters from a binarized image; identifies a combination of pose parameters for which the number of cross surfaces of parameter surfaces that accord with surface parameter formulas, which are numerical formulas for expressing a reference surface, is a maximum; finds a slope weighting for each of cross pixels, which are pixels on each candidate surface and which are pixels within a prescribed range, that is identified based on the angles of the tangent plane at the cross pixel and based on planes formed by each of the axes of parameter space; and identifies the significant candidate surface for which a number, which is the sum of slope weightings, is a maximum, as the actual surface that is the reference surface that actually exists in the image.

Abstract: In a pose estimation for estimating the pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating a pose, a data processing device: extracts pose parameters from a binarized image; identifies a combination of pose parameters for which the number of cross surfaces of parameter surfaces that accord with surface parameter formulas, which are numerical formulas for expressing a reference surface, is a maximum; finds a slope weighting for each of cross pixels, which are pixels on each candidate surface and which are pixels within a prescribed range, that is identified based on the angles of the tangent plane at the cross pixel and based on planes formed by each of the axes of parameter space; and identifies the significant candidate surface for which a number, which is the sum of slope weightings, is a maximum, as the actual surface that is the reference surface that actually exists in the image.

Abstract: An object detection and tracking support system includes a setting unit, a transmission level obtaining unit, a propagation loss function estimating unit that, based on various information relating to a transmitter and a receiver stored in the setting unit, calculates the propagation loss as a propagation loss function expressed as a function of the distance and the direction viewed from the receiver, a target strength obtaining unit that, in regard to an object of object information stored in the setting unit, extracts a target strength of the object from an external database; and a detection signal level function estimating unit that, based on transmission level information obtained by the transmission level obtaining unit, a propagation loss function calculated by the propagation loss coefficient estimating unit, and a target strength extracted by the target strength obtaining unit, determines a detection signal level function, for display on an external display unit.

Abstract: A target tracking system which tracks targets using a plurality of virtual particles includes a detector which detects the targets based on a signal wave from the targets and outputs a detected results as a detected target positions, a fluctuation distribution unit which generates fluctuations arising from at least disturbances and measurement errors, and an estimation unit which sets virtual particles based on the fluctuations and estimates a true target positions based on the detected target positions.

Abstract: To provide a target detection system including transmitters/receivers constituted with radars, sonars, or lidars, which is capable of effectively capturing a target even under an environment where the S/N ratio is low and reflected signals may be buried under noises. The target detection system is characterized to include at least two target-detecting transmitters/receivers capable of performing azimuth setting placed at different placing positions from each other; and a main control device including a position calculating module which specifies a position of a target based on reflection information regarding the azimuth of the target detected by each of the transmitters/receivers, wherein the position calculating module includes a function which specifies the position of the target through performing superimposing processing of information regarding the azimuth of the target acquired by the two transmitters/receivers on the basis of positional information of each of the transmitters/receivers.

Abstract: Provided is a technique capable of suppressing the deterioration in azimuth resolution and distance resolution in even a modulated and transmitted or received signal or a signal reflected by an object and varied in intensity when acquiring waveform information. A measurement device comprise: a plurality of sensors which receive waves propagating through a space; and a sampling timing calculation means which obtains, on the basis of the relative positions of the sensors and the velocities of the waves, the difference between the arrival times of the waves received by the respective sensors and calculates, for each sensor, sampling timing for acquiring the waveform information relating to the waves, on the basis of the difference between the arrival times.

Abstract: A rotation estimation device includes an attitude determination section that accepts a plurality of three-dimensional images captured by an image capturing device at a plurality of timings, detects a plane region that is present in common with the plurality of images, and obtains a relative attitude of the image capturing device to the plane region in the image based on the image for each of the plurality of images; and a rotation state estimation section that obtains a rotational state of the image capturing device based on the relative attitude of the image capturing device, the relative attitude being obtained for each of the images.

Abstract: In a pose estimation for estimating the pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating a pose, a data processing device: extracts pose parameters from a binarized image; identifies a combination of pose parameters for which the number of cross surfaces of parameter surfaces that accord with surface parameter formulas, which are numerical formulas for expressing a reference surface, is a maximum; finds a slope weighting for each of cross pixels, which are pixels on each candidate surface and which are pixels within a prescribed range, that is identified based on the angles of the tangent plane at the cross pixel and based on planes formed by each of the axes of parameter space; and identifies the significant candidate surface for which a number, which is the sum of slope weightings, is a maximum, as the actual surface that is the reference surface that actually exists in the image.

Abstract: A CAD data compressing method is disclosed, that comprises the steps of generating a component figure list, and generating data of a plurality of pattern groups each containing a pointer to a component figure of the component figure list.

Abstract: The invention provides a subpixel accuracy registration technique where accuracy is not lost even where an image is subjected to deformation due to influences of the characteristics of the imaging device or noise. A fitting range setting device 105, sets a range of pixels of an input image with large differential values as a fitting range. A function fitting device 104, fits a mono-peak function for each fitting range, and obtains the edge position at subpixel accuracy. Registration is then effected with a pixel accuracy registration device 107. A corresponding candidate curve generating device 108, with respect to an edge point on a certain one image, makes a corresponding plurality of edge points on an other image corresponding candidate curves joined in a curve.

Abstract: An image differential unit differentiates an inspection image and a reference image on an object to be inspected. An image division unit divides an image into a predetermined number of divisions. Pixel precision position alignment unit overlays the inspection image and the reference image by carrying out the position alignment in pixel precision which is a pixel size precision. Function fitting unit detects an edge, and obtains intensity profile of the absolute pixel value in the direction orthogonal with the edge, and fits a predetermined single peak function to it. Sub-pixel precision position displacement computing unit computes a difference of the corresponding edge positions as the sub-pixel precision position displacement. Adjusted differential image forming unit forms the adjusted differential image by rewriting the pixel value so that the intensity profile of the pixel value in the direction orthogonal with the edge should follow the single peak type function form on the corresponding two edges.

Abstract: Graphic data conversion method and graphic data conversion apparatus enable appropriate graphic data for a fault inspection equipment to be provided, in which unprepared increase of data-volume is avoided even when CAD data of a graphic form drawing equipment is made to convert into graphic data for the fault inspection equipment, and it is prevented that processing speed of the fault inspection equipment decreases caused by unnecessary region division. Graphic data whose region is divided among the CAD data is made to unify for generating graphic data which represents the whole original graphic form. Thereafter, the optimum graphic data for the fault inspection equipment is made to fleshly generate from the aforementioned graphic data in such a way as to match division-region that is determined by a file format of the fault inspection equipment.

Abstract: A CAD data compressing method is disclosed, that comprises the steps of generating a component figure list, and generating data of a plurality of pattern groups each containing a pointer to a component figure of the component figure list.