Abstract: A fundamental matrix generation apparatus performs: detecting three or more feature point pairs from a first image and a second image; detecting, for each of the feature point pairs, a derived point pair that is a pair of a derived point separated by a first distance in a first direction from a point on the first image included in the feature point pair and a derived point separated by a second distance in a second direction from a point on the second image included in the feature point pair; generating a fundamental matrix or the fundamental matrix representing an epipolar constraint on a point on the first image and a point on the second image by using the detected feature point pairs and derived point pairs.

Abstract: In a camera calibration apparatus, a vanishing point calculation uni calculates a “first vanishing point” in the horizontal direction based on a first coordinate pair and a second coordinate pair acquired by an acquisition unit and calculates a “second vanishing point” in the vertical direction based on a third coordinate pair and a fourth coordinate pair acquired by the acquisition unit. The camera parameter calculation unit calculates a camera parameter of a camera based on the first vanishing point and the second vanishing point calculated by the vanishing point calculation unit. Each of the first coordinate pair and the second coordinate pair is related to a part of a human horizontally distributed in a world coordinate space. Each of the third coordinate pair and the fourth coordinate pair is related to a part of a human vertically distributed in the world coordinate space.

Abstract: An essential matrix generation apparatus performs: detecting three or more feature point pairs from a first image and a second image; detecting, for each of two or more of the feature point pairs, a derived point pair that is a pair of a derived point separated by a first distance in a first direction from a point on the first image included in the feature point pair and a derived point separated by a second distance in a second direction from a point on the second image included in the feature point pair; generating an essential matrix representing an epipolar constraint on a point on the first image and a point on the second image by using the detected feature point pairs and derived point pairs.

Abstract: In the object detection device, the plurality of object detection units output a score indicating a probability that a predetermined object exists, for each partial region set with respect to image data inputted. The weight computation unit computes a weight for each of the plurality of object detection units by using weight computation parameters and based on the image data. The weights are used when the scores outputted by the plurality of object detection units are merged. The weight redistribution unit changes the weight for a predetermined object detection unit, among the weights computed by the weight computation unit, to 0 and output the weights. The merging unit merges the scores outputted by the plurality of object detection units for each of the partial regions, by using the weights computed by the weight computation unit and including the weight changed by the weight redistribution unit.

Abstract: A camera parameter estimation apparatus: takes three sets of three-dimensional coordinates pertaining to an object and two-dimensional coordinates corresponding to the three-dimensional coordinates, and transforms a coordinate system of the three-dimensional coordinates from a world coordinate system to a local coordinate system; calculates a linear transformation matrix based on a projection transformation expression from the transformed three-dimensional coordinates to the two-dimensional coordinates, calculates a coefficient of a quartic equation pertaining to any one of depths from a camera center to each three-dimensional coordinate, and calculates each depth; calculates the rotation matrix in the local coordinate system using each depth and the linear transformation matrix; calculates a translation vector in the local coordinate system from each depth based on the projection transformation expression; and calculates a rotation matrix and a translation vector in the world coordinate system by performing

Abstract: A training data generation device according to the present invention includes: a memory; and at least one processor coupled to the memory. The processor performs operations. The operations including: selecting, from items included in any of a state of a road, a type of the road, a type of sensor information for determining the state of the road, an acquisition condition of the sensor information and an external environment in an acquisition of the sensor information, a combination including at least two or more of the items; and extracting the sensor information using the combination as training data to be used for training a model for determining the state of the road using the sensor information.

Abstract: An image processing apparatus (10) includes an image processing unit (110) and a risk information generation unit (120). The image processing unit (110) acquires and processes an image generated by an image capture apparatus (20), that is, an image including a plurality of persons. As an example, the image processing unit (110) sets a person being at least part of the plurality of persons as a reference person and computes a distance (first distance) between the reference person and the closest person to the reference person. By using the first distance, the risk information generation unit (120) generates infection risk information in a target region being an image capture target of the image capture apparatus (20).

Abstract: A camera parameter estimation apparatus 10 for estimating geometric parameters of a camera that has shot an image of an object and a lens distortion parameter of a lens distortion model represented by a single unknown. The camera parameter estimation apparatus 10 includes: a data obtaining unit 11 that obtains image corresponding points relating to the object and an approximation order for polynomial approximation of the lens distortion model; and a parameter estimation unit 12 that estimates, based on the image corresponding points and the approximation order, the geometric parameter and the lens distortion parameter that minimize an error function representing a specific transformation of the image corresponding points.

Abstract: A homography matrix generation apparatus (2000) detects two or more key-point pairs from a first image (10) and a second image (20). The homography matrix generation apparatus (2000) detects, for each of the key-point pairs, a derived point pair, which is a pair of a point separated by a first distance in a first direction from a point on the first image (10) included in the key-point pair and a point separated by a second distance in a second direction from a point on the second image (20) included in the key-point pair. The homography matrix generation apparatus (2000) uses each of the detected key-point pairs and the derived point pairs to generate a homography matrix (40) representing a homography from a point on the first image (10) to a point on the second image (20).

Abstract: A state determination device according to the present invention includes: a memory; and at least one processor coupled to the memory. The processor performs operations. The operations including: combining output from a plurality of determination models for an input image of a road, the plurality of determination models each learned using training data in which at least one of a state of a moving object mounting an imaging device that acquires an image of the road, a state of the road, and an external environment is different.

Abstract: In a camera calibration apparatus (10), an acquisition unit (11) acquires a first normal vector in an image plane and a second normal vector in the image plane respectively corresponding to a first normal vector in a world coordinate space and a second normal vector in the world coordinate space which are normal vectors with respect to a reference plane in the world coordinate space and have the same length. A projective depth calculation unit (12) calculates a projective depth vector having, as vector elements, four projective depths respectively corresponding to a start point and an end point of the first normal vector in the image plane and a start point and a end point of the second normal vector in the image plane.

Abstract: An apparatus includes an acquisition means for acquiring displacement quantity in a time-series manner, the displacement quantity being generated at a measurement part of a structure by the weight of a vehicle that travels on the structure, a detection means for detecting the size of the vehicle that passes through the structure and detecting the type of the vehicle from the size, and a control means for controlling the acquisition means on the basis of the detected type of the vehicle.

Abstract: An image processing apparatus includes at least one memory configured to store instructions, and at least one processor configured to execute the instructions to process an image of a target region, and thereby compute a proximity index being an index relating to a proximity state of a plurality of persons captured in the image, and cause a predetermined apparatus to execute predetermined control, when the proximity index satisfies a criterion.

Abstract: A vibration measurement apparatus 30 includes a detection unit 31 that acquires, as a pattern image from an image capturing apparatus 20 that shoots a measurement target surface of a structure 40, an image of the measurement target surface onto which pattern light is projected by an optical apparatus 10, and detects the pattern light from the pattern image, an estimation unit 32 that estimates an angle between the normal of the image capturing surface and the normal of the measurement target surface, based on the pattern light, an image conversion unit 33 that converts the shot image into an image that would be obtained were the normal of the measurement target surface coincident with the normal of the image capturing surface of the image capturing apparatus 20, using the estimated angle, and a vibration measurement unit 34 that measures the vibration of the structure 40 using the converted image.

Abstract: An image processing apparatus (10) includes an image processing unit (110) and a risk information generation unit (120). The image processing unit (110) acquires and processes an image generated by an image capture apparatus (20), that is, an image including a plurality of persons. As an example, the image processing unit (110) sets a person being at least part of the plurality of persons as a reference person and computes a distance (first distance) between the reference person and the closest person to the reference person. By using the first distance, the risk information generation unit (120) generates infection risk information in a target region being an image capture target of the image capture apparatus (20).

Abstract: The present invention provides an image processing apparatus (10) that includes: a feature value extraction unit (11) that, by processing an image including a plurality of persons, extracts an external appearance feature value of each of the persons; and a determination unit (12) that, by processing the image, determines another of the persons who satisfies an infection condition between him/her and each of the persons, and registers relevant information relating to the determined another person in association with the external appearance feature value of each of the persons.

Abstract: The present invention provides an image processing apparatus (10) including: a companion determination unit (12) that determines a companion of each of a plurality of persons detected from an image, based on the image; a distance computation unit (13) that computes a first distance being a distance to the nearest person among the persons other than a companion, for the each person; and a risk information generation unit (14) that generates, with use of the first distance, infection risk information being information related to a risk of getting an infectious disease or a safety rate of not getting an infectious disease within a target region being a region included in the image.

Abstract: An image processing apparatus includes an image processing unit and a risk information generation unit. By processing at least one image, the image processing unit identifies a caution-requiring location being a location where a proximity indicator being an indicator related to a proximity state between a plurality of persons satisfies a criterion. The risk information generation unit outputs information indicating the caution-requiring location. For example, the information is displayed on a display unit through a display control unit. For each person, the image processing unit computes a first distance being the distance to the closest person to the person. Then, for each of a plurality of locations, the image processing unit counts the number of times the first distance has a reference value or less. Then, the proximity indicator is set by using the number of times the first distance has the reference value or less.

Abstract: A projection transformation parameter for guaranteeing a deformation to a convex quadrilateral can be calculated even when one or more of correspondence points are errors. A projection transformation parameter estimation device according to an embodiment includes a correspondence point detection unit (1) configured to detect information about a correspondence between two pieces of input data, a quadratic surface calculation unit (2) configured to fit a quadratic surface to the information about the correspondence for one or both of the two pieces of the input data, and a projection transformation matrix calculation unit (3) configured to calculate a projection transformation parameter between the two pieces of the input data by using the information about the correspondence with a constraint condition specifying that a property of the quadratic surface is maintained even after projection transformation.

Abstract: An information learning system includes: a condition generation unit that generates a condition from training data that are inputted to a neural network; a condition connection unit that connects the condition to a feature quantity of the training data; and an optimization unit that optimizes a parameter of the neural network by using the feature quantity to which the condition is connected. The condition generation unit includes a temperature sampling unit that probabilistically changes a temperature of activation. This makes it possible to appropriately perform the learning of a conditional neural network.