Abstract: A non-transitory computer-readable storage medium storing an information processing program that causes at least one computer to execute a process, the process includes acquiring video data that has target objects that include a person and an object; specifying each relationship of each of the target objects in the acquired video data by using graph data that indicates a relationship of each of target object stored in a storage unit; specifying a behavior of the person in the acquired video data by using a feature of the person; and predicting a future behavior of the person or a state of the person by comparing the specified behavior of the person and the specified relationship with a behavior prediction rule, the behavior prediction rule being a rule associated with a future behavior of a person for each combination of a behavior of the person and a relationship.

Abstract: A non-transitory computer-readable recording medium stores therein an estimation program that causes a computer to execute a process including, identifying a first person who uses a first cart from a first image acquired by capturing inside a store, generating skeleton information of the first person, acquiring, by using the skeleton information, a first space in which the first person grasps a grip part of the first cart, and estimating a first scale of the first person based on the first space and length information of the first cart.

Abstract: A distance measuring device is configured to: obtain a first distance image acquired from a time of flight (TOF) sensor and a polarized image generated by calculating a degree of polarization for each pixel based on a plurality of images acquired from a plurality of cameras that receives linearly polarized light with different polarization directions; and execute a process for calculating reliability according to a difference between a time of measuring a distance and a time of photographing the plurality of images for each pixel of the first distance image, and execute a process for calculating a distance from the TOF sensor to a subject for each pixel using a second distance image calculated by weighting the reliability to a distance of each pixel of the first distance image, and a third distance image calculated by estimating a distance of each pixel based on the polarized image.

Abstract: A memory stores shape information representing a shape of an object. A processor detects a plurality of feature lines from an image of an object that has been captured by an image capturing device in a manufacturing process of manufacturing the object, and produces a plurality of combinations by correlating each of a plurality of line segments in the shape information and each of the plurality of feature lines with each other. Next, the processor performs classification of each of the combinations into an identified combination that has a certain correlation result or an unidentified combination that has an uncertain correlation result. The processor also changes a result of the classification for the identified combination and the unidentified combination according to a reliability of each of the plurality of combinations and determines a degree of progress of the manufacturing process by using the identified combination included in the changed result.

Abstract: An image processing method includes: detecting a plurality of feature lines from a first image captured from a first position; specifying, based on a positional relationship between the plurality of feature lines and a plurality of projection lines generated by projecting each of a plurality of line segments onto the first image, a feature line representing a defective portion of a shape of an object; setting a plurality of candidate positions based on the first position, each of the plurality of candidate positions being a candidate for a second position at which a second image is captured; calculating an evaluation value of each of the plurality of candidate positions; determining any of the plurality of candidate positions based on the evaluation value of each of the plurality of candidate positions; and outputting first information to be used in recognition of the determined candidate position.

Abstract: A processor detects feature lines from an image of an object and generates projection lines by projecting line segments in shape information of the object on the image. The processor generates combinations each including a feature line and a projection line and generates plural sets each including a specific number of combinations. The processor uses each set to estimate a position and an orientation of an imaging device that has captured the image, and evaluates a result of the estimation for each set. When there is a change in a relative position or orientation between the object on the image and a shape represented by the shape information, the processor repeats generation of the plural sets, estimation of the position and the orientation of the imaging device and evaluation of the estimation result. The processor determines the position and the orientation of the imaging device based on the repeated evaluation.

Abstract: An image processing apparatus includes: a memory that stores shape information including a plurality of line segments representing a shape of an object; and a processor. The processor is configured to: detect a plurality of feature lines from an image of the object, generate a target projection line by projecting any of the plurality of line segments over the image of the object, extract a feature line overlapping with a predetermined region based on the target projection line over the image of the object from the plurality of feature lines to generate a set of feature lines, and select a target feature line from the set of feature lines based on gradient information indicating a gradient of pixel values over the image of the object, and calculate a deviation amount between a line segment corresponding to the target projection line and the target feature line.

Abstract: A data management system includes an information processing device and a data management device. The information processing device acquires an overall map from a storage in the data management device, estimates a location of the moving object at the time of capturing each of peripheral images that are determined to correspond to any of the key frame images which are stored in the storage among the peripheral images, and generate a local map representing each of the peripheral images which are determined as the key frame image. The management device updates a portion, corresponding to the local map, of the overall map stored in the storage based on the local map.

Abstract: An inspection apparatus includes a memory for storing shape information including a plurality of line segments representing a shape of an object; and a processor coupled to the memory and the processor that detects a plurality of feature lines from an image of the object, generates a plurality of combinations obtained by correlating each of the plurality of line segments and each of the plurality of feature lines with each other, generates a plurality of projection lines by projecting each of the plurality of line segments onto the image, sets a threshold value with respect to an error between a position of the projection lines and a position of the feature lines of the line segments included in each of the plurality of combinations based on a statistical value of the error, and classifies the plurality of combinations using the threshold value.

Abstract: An image processing method includes: detecting a plurality of feature lines from a first image captured from a first position; specifying, based on a positional relationship between the plurality of feature lines and a plurality of projection lines generated by projecting each of a plurality of line segments onto the first image, a feature line representing a defective portion of a shape of an object; setting a plurality of candidate positions based on the first position, each of the plurality of candidate positions being a candidate for a second position at which a second image is captured; calculating an evaluation value of each of the plurality of candidate positions; determining any of the plurality of candidate positions based on the evaluation value of each of the plurality of candidate positions; and outputting first information to be used in recognition of the determined candidate position.

Abstract: An image processing apparatus includes: a memory that stores shape information including a plurality of line segments representing a shape of an object; and a processor. The processor is configured to: detect a plurality of feature lines from an image of the object, generate a target projection line by projecting any of the plurality of line segments over the image of the object, extract a feature line overlapping with a predetermined region based on the target projection line over the image of the object from the plurality of feature lines to generate a set of feature lines, and select a target feature line from the set of feature lines based on gradient information indicating a gradient of pixel values over the image of the object, and calculate a deviation amount between a line segment corresponding to the target projection line and the target feature line.

Abstract: An estimation device includes a processor coupled to a memory and configured to detect a plurality of feature lines from an image of the object photographed by an imaging device, generate a plurality of sets of a predetermined number of line segments among the plurality of line segments, select a set to be processed from among the plurality of sets based on a length-first selection order in which a line segment that is longer than other line segments is preferentially selected, generate the predetermined number of combinations in which the predetermined number of line segments included in the set to be processed and the predetermined number of feature lines among the plurality of feature lines are associated with each other on a one-to-one basis, and estimate a position and a orientation of the imaging device in a three-dimensional space using the predetermined number of combinations.

Abstract: A processor detects feature lines from an image of an object and generates projection lines by projecting line segments in shape information of the object on the image. The processor generates combinations each including a feature line and a projection line and generates plural sets each including a specific number of combinations. The processor uses each set to estimate a position and an orientation of an imaging device that has captured the image, and evaluates a result of the estimation for each set. When there is a change in a relative position or orientation between the object on the image and a shape represented by the shape information, the processor repeats generation of the plural sets, estimation of the position and the orientation of the imaging device and evaluation of the estimation result. The processor determines the position and the orientation of the imaging device based on the repeated evaluation.

Abstract: A memory stores shape information representing a shape of an object. A processor detects a plurality of feature lines from an image of an object that has been captured by an image capturing device in a manufacturing process of manufacturing the object, and produces a plurality of combinations by correlating each of a plurality of line segments in the shape information and each of the plurality of feature lines with each other. Next, the processor performs classification of each of the combinations into an identified combination that has a certain correlation result or an unidentified combination that has an uncertain correlation result. The processor also changes a result of the classification for the identified combination and the unidentified combination according to a reliability of each of the plurality of combinations and determines a degree of progress of the manufacturing process by using the identified combination included in the changed result.

Abstract: An information processing apparatus configured to store a plurality of images captured by an imaging device, store first position information and first orientation information indicating positions and orientations of the imaging device in capturing of each of the plurality of images, identify, among from the plurality of images, a first image resembling a second image, identify a first area included in the first image, identify a second area, included in the second image, corresponding to the first area, identify second position information and second orientation information indicating a position and an orientation of the imaging device respectively in capturing of the second image, based on a comparison between a first luminance of a first pixel included in the first area and a second luminance of a second pixel included in the second area and the first position information and the first orientation information of the first image.

Abstract: A display control method includes, displaying a first plurality of edge lines extracted from an image that includes a manufactured article, accepting designation for a second plurality of edge lines selected from the displayed first plurality of edge lines, identifying pairs each of which includes an edge line of the second plurality of edge lines and a line of a plurality of lines corresponding to the edge line, the plurality of lines being included in a three-dimensional model, determining a specific display posture of the three-dimensional model such that a positional relation between a first edge line and a first line included in a first pair satisfies a condition and a position of a second edge line and a position of a second line included in a second pair correspond to each other, and superimposing, in accordance with the specific display posture, the three-dimensional model on the image.

Abstract: A method includes specifying a position of a virtual object based on a position of a map point that is defined in a first map and indicates three-dimensional coordinates of a feature point, correcting the position of the virtual object based on positions of a plurality of map points defined in a second map and a capturing direction of a camera when the first map is changed to the second map that is different from the first map, and controlling a display to display the virtual object, based on the corrected position of the virtual object and an image captured by the camera.

Abstract: An inspection apparatus includes a memory for storing shape information including a plurality of line segments representing a shape of an object; and a processor coupled to the memory and the processor that detects a plurality of feature lines from an image of the object, generates a plurality of combinations obtained by correlating each of the plurality of line segments and each of the plurality of feature lines with each other, generates a plurality of projection lines by projecting each of the plurality of line segments onto the image, sets a threshold value with respect to an error between a position of the projection lines and a position of the feature lines of the line segments included in each of the plurality of combinations based on a statistical value of the error, and classifies the plurality of combinations using the threshold value.

Abstract: An estimation device includes a processor coupled to a memory and configured to detect a plurality of feature lines from an image of the object photographed by an imaging device, generate a plurality of sets of a predetermined number of line segments among the plurality of line segments, select a set to be processed from among the plurality of sets based on a length-first selection order in which a line segment that is longer than other line segments is preferentially selected, generate the predetermined number of combinations in which the predetermined number of line segments included in the set to be processed and the predetermined number of feature lines among the plurality of feature lines are associated with each other on a one-to-one basis, and estimate a position and a orientation of the imaging device in a three-dimensional space using the predetermined number of combinations.

Abstract: A data management system includes an information processing device and a data management device. The information processing device acquires an overall map from a storage in the data management device, estimates a location of the moving object at the time of capturing each of peripheral images that are determined to correspond to any of the key frame images which are stored in the storage among the peripheral images, and generate a local map representing each of the peripheral images which are determined as the key frame image. The management device updates a portion, corresponding to the local map, of the overall map stored in the storage based on the local map.