Abstract: An object recognition processing apparatus includes: an image obtainment unit that obtains an image; a template matching unit that obtains a recognition result including a plurality of candidates for the object to be recognized by carrying out a template matching process on the image; a candidate exclusion processing unit that excludes a candidate that meets a predetermined condition by generating, for each of the plurality of candidates, a binary image of the object to be recognized, and finding a degree of overlap of each candidate using the binary image; and a recognition result output unit that outputs a candidate that remains without being excluded as a recognition result.

Abstract: A three-dimensional detailed position/orientation estimation apparatus includes a first position/orientation estimation unit and a second position/orientation estimation unit that are configured to estimate three-dimensional position and orientation. The first position/orientation estimation unit optimizes six parameters (translations x, y, and z, and rotations ?, ?, and ?) using 3D data, and the second position/orientation estimation unit optimizes only three parameters (translations x and y, and rotation ?) that can be estimated with high accuracy using a 2D image, based on the result of the three-dimensional position/orientation estimation performed by the first position/orientation estimation unit using the 3D data.

Abstract: An image processing device is provided with a storage unit configured to store for each model among a plurality of models, a model template obtained by reducing a model image; an image reduction unit configured to reduce an input image by the reduction ratio for each model; and a search unit configured to search for the location of a model in an input image on the basis of a reduced input image and a model template. The storage unit stores model templates for at least two of the models wherein said model templates are obtained by reducing the model images by the same reduction ratio; and The image reduction unit processes the at least two models jointly. The image processing device is hereby capable of high-speed identification and recognition of a plurality of models from an input image.

Abstract: A gripping method relates to a gripping method for gripping an object using a multi-fingered hand provided with a plurality of fingers. A three-dimensional measurement sensor is used to measure an area that contains the object to obtain three-dimensional information. If the area includes an area for which no three-dimensional information can be obtained, the area is separated and is interpolated using the range information indicating the closer one of distances obtained at two positions on an axis extending along a direction in which the fingers are opened and closed, the two positions being adjacent to the unmeasured area with the unmeasured area interposed therebetween. Then, the distance between the fingers for gripping the object is decided, and the multi-fingered hand is controlled based on the distance.

Abstract: A gripping method relates to a method for gripping an object using a multi-fingered hand provided with a plurality of fingers. The method includes measuring, using a three-dimensional measurement sensor, an area that contains the object, and obtaining three-dimensional information for each position within the area, and deciding positions of the plurality of fingers for gripping the object, by classifying the area, if the area includes a measured area for which the three-dimensional information could be obtained and an unmeasured area for which the three-dimensional information could not be obtained, into the measured area and the unmeasured area based on the distance-indicating information, the positions of the plurality of fingers being decided based on positions of the unmeasured area.

Abstract: A template creation apparatus includes a three-dimensional data acquisition unit that acquires three-dimensional data of an object that is a recognition target, a normal vector calculation unit that calculates a normal vector at a feature point of an object viewed from a predetermined viewpoint that is set for the object, a normal vector quantization unit that quantizes a normal vector by mapping the normal vector to a reference region on a plane orthogonal to an axis that passes through the viewpoint, so as to acquire a quantized normal direction feature amount, the reference region including a central reference region corresponding to the vicinity of the axis and a reference region in the periphery of the central reference region, a template creation unit that creates a template for each viewpoint based on the quantized normal direction feature amount, and a template information output unit that outputs the template.

Abstract: A viewpoint position-related parameter setting unit determines which approximate spherical shape to use in order to determine a viewpoint position. A viewpoint position creation unit creates a plurality of approximate spherical shapes set by the viewpoint-position-related parameter setting unit, and creates respective viewpoint positions. An optimal viewpoint position creation unit calculates a rotation angle at which the number of slave viewpoints associated with master viewpoints is substantially equal and a maximum distance between the master viewpoint and the slave viewpoint associated therewith is a minimum.

Abstract: To allow users who usually play games on a personal computer to enter input to game consoles for domestic use without being stressed. A controller system for game consoles is made up of a game console controller 100 and a mouse 200. The mouse 200 is identical to an ordinary mouse. The game console controller 100 has a structure resembling a part of a keyboard that is used for common personal computers and equipped with at least six keys 120 in a 2-by-3 array. The mouse 200 and the game console controller 100 can be attached to and removed from each other via a cable 210 extending from the mouse 200. The connection between them is an USB connection.

Abstract: A standard template generation unit generates a plurality of standard templates with different resolutions for different layers. An identification template generation unit generates, for each layer, a common template that represents a common part of the plurality of standard templates, and identification templates that represent differences between the plurality of templates. Matching in a higher level layer uses the standard templates. Matching in a lower level layer uses the common template representing a common part of the templates and the identification templates representing differences between the templates.

Abstract: An image processing apparatus includes a scale-down factor determination unit that generates two-dimensional images of an object viewed from a plurality of viewpoints using three-dimensional data representing a three-dimensional shape of the object and determines a scale-down factor for each viewpoint, a template generation unit that scales down the generated two-dimensional image from each viewpoint using the scale-down factor determined for the viewpoint and calculates a feature quantity from a scaled-down image to generate a template, and a template information output unit that outputs, for each viewpoint, the template and the scale-down factor used for generating the template in a manner associated with each other.

Abstract: An image recognition device includes an identification unit configured to compare a feature point in an input image and a feature point in every model image to compute a first degree of similarity between the input image and the model image, and to identify the input image on the basis of said first degree of similarity. To compute the first degree of similarity for a model image, the identification unit adds to a score based on a matching feature point for each feature point in the model image matching a feature point in the input image. The score based on the matching feature point is a value that increases as the number of model images including the matching feature point decreases.

Abstract: The coarse-to-fine search method includes: a first search step of detecting an object from a first image by means of template matching; and a second step of setting an area comprising n×m pixels within a second image having resolutions of horizontal n times and vertical m times as compared with the first image corresponding to a position detected in the first search step as a search range and detecting the object from the second image by means of template matching. During the coarse-to-fine search, data for the second image are rearranged on a work memory prior to the second search step such that data of the n×m pixels collated with same components of a template are stored in contiguous memory addresses, and n×m collation operations for the n×m pixels are executed in less than n×m calculation by SIMD commands in the second search step.

Abstract: An image comparison device includes: a storage in which a model image is stored, the model image including a position of a feature point of a comparison object and a luminance gradient direction at the position of the feature point; a feature amount acquisition unit configured to acquire the position of the feature point and the luminance gradient direction at the position of the feature point from an input image; and an image comparison unit configured to compare the model image and the input image. The image comparison unit performs image comparison by providing an allowable range in both the position of the feature point and the luminance gradient direction at the position of the feature point position.

Abstract: A template creation device includes an acquisition unit configured to acquire a plurality of templates from a plurality of images of different poses of a single object, or a plurality of images for a plurality of objects; a clustering unit configured to divide the plurality of templates into a plurality of groups on the basis of a similarity score; and an integration unit configured to combine the templates in a group into an integrated template, and to create a new template set from the plurality of integrated templates corresponding to each group in the plurality of groups.

Abstract: A game apparatus includes a CPU, the CPU judges a motion of a player on the basis of a cycle of a load value input from a load controller, and selectively displays an animation of a player object according to the motion. Furthermore, the CPU controls a moving amount or a moving velocity of the player object on the basis of the load value input from the load controller, and controls a moving direction of the player object according to a barycentric position of the player detected by the load controller.

Abstract: An image processing device is provided with a storage unit configured to store for each model among a plurality of models, a model template obtained by reducing a model image; an image reduction unit configured to reduce an input image by the reduction ratio for each model; and a search unit configured to search for the location of a model in an input image on the basis of a reduced input image and a model template. The storage unit stores model templates for at least two of the models wherein said model templates are obtained by reducing the model images by the same reduction ratio; and The image reduction unit processes the at least two models jointly. The image processing device is hereby capable of high-speed identification and recognition of a plurality of models from an input image.

Abstract: An image recognition device includes an identification unit configured to compare a feature point in an input image and a feature point in every model image to compute a first degree of similarity between the input image and the model image, and to identify the input image on the basis of said first degree of similarity. To compute the first degree of similarity for a model image, the identification unit adds to a score based on a matching feature point for each feature point in the model image matching a feature point in the input image. The score based on the matching feature point is a value that increases as the number of model images including the matching feature point decreases.

Abstract: An image comparison device includes: a storage in which a model image is stored, the model image including a position of a feature point of a comparison object and a luminance gradient direction at the position of the feature point; a feature amount acquisition unit configured to acquire the position of the feature point and the luminance gradient direction at the position of the feature point from an input image; and an image comparison unit configured to compare the model image and the input image. The image comparison unit performs image comparison by providing an allowable range in both the position of the feature point and the luminance gradient direction at the position of the feature point position.

Abstract: An image matching method performed by an image matching device, includes acquiring a model image, generating a plurality of variation images by applying to the model image variations that are different from each other, extracting features from each of the plurality of variation images, generating a model template based on the features, and performing template matching using an image to be matched and the model template.