Abstract: The image processing device comprises: a storage section storing a three-dimensional shape model in which feature amounts and three-dimensional positional information, for multiple feature points of a target object, are associated; an extraction process section configured to extract the feature amounts and two-dimensional positional information of the feature points from a two-dimensional image of the target object captured with a camera; and a recognition process section configured to identify three-dimensional positional information of the feature points of the two-dimensional image and recognize the position and orientation of the target object by matching the feature points of the two-dimensional image with the feature points of the three-dimensional model using the feature amounts.

Abstract: An image processing device, for use in a mounting device, detects a shape of the main body, positions of protruding sections, a number of the protruding sections, and a distal end portion of the protruding section of the mounting device from a captured image of the protruding section radiated with light from side with respect to the component and the main body radiated with light from below with respect to the component. The image processing device acquires information of the insertion sections, and generates a component model including a contour shape model including the shape and the direction of the main body and a protruding section model including the positions and the number of the protruding sections, and a feature of the distal end portion of the protruding section.

Abstract: A height measurement device images a target, extracts a contour of the target from a two-dimensional image, sets a circumscribed rectangular area of which each side is parallel to a corresponding side of the visual field of the camera and each side is circumscribed with the extracted contour of the target, and sets an extension area in which each of four sides of the set circumscribed rectangular area is extended outward by a predetermined amount. The height measurement device determines multiple imaging positions such that maximum parallax is obtained within a range where the extension area does not protrude from the visual field of the camera. Then, the height measurement device images the target at each of the determined multiple imaging positions, and estimates a height of the target from parallax of a two-dimensional image of the target imaged at each of the multiple imaging positions.

Abstract: A work robot sequentially holds multiple workpieces supplied to a supply area and moves the held workpieces to a work area. The work robot includes an image-capturing device configured to capture images of the multiple workpieces supplied to the supply area in random orientations and positions, an image processing device configured to recognize multiple workpiece regions from the images captured by the image-capturing device, obtain an area and a position of each of the recognized multiple workpiece regions, and obtain a distance between each workpiece region and the work area or the work robot, and a control device configured to determine a holding order of the workpiece based on the areas of the multiple workpiece regions and the distance between each workpiece region and the work area or the work robot as obtained by the image processing device.

Abstract: A work machine includes a pickup member configured to pick up a component; a storage device configured to store positional information on multiple pickup positions where the pickup member can pick up the component; a recognition device configured to optically recognize a multiple of the component including the pickup target; and a control device configured to select, from the multiple pickup positions of the pickup target component, one pickup position which is less likely to interfere with other components based on the positional information and a recognition result from the recognition device, and cause the pick member to pick up the pickup target component at the one selected pickup position.

Abstract: The image processing device comprises: a storage section storing a three-dimensional shape model in which feature amounts and three-dimensional positional information, for multiple feature points of a target object, are associated; an extraction process section configured to extract the feature amounts and two-dimensional positional information of the feature points from a two-dimensional image of the target object captured with a camera; and a recognition process section configured to identify three-dimensional positional information of the feature points of the two-dimensional image and recognize the position and orientation of the target object by matching the feature points of the two-dimensional image with the feature points of the three-dimensional model using the feature amounts.

Abstract: Data structure for image-processing data is for creating image-processing data necessary for performing image processing on captured images of multiple workpieces when an articulated robot extracts a workable target workpiece from among multiple supplied workpieces. The data structure includes workpiece shape data for recognizing a target workpiece by pattern matching and tool data configured to check whether there is interference between a tool mounted on the articulated robot and a peripheral workpiece. The data structure is configured such that the combination of the workpiece shape data and the tool data can be rearranged for each workpiece or for each tool.

Abstract: A robot system for performing drive control of a robot arm with respect to a target object according to information obtained by a camera, including a robot having a working section, a camera mounted in the vicinity of the working section, and a control device for controlling the driving of the robot while confirming the target object based on image data of the camera, is provided. The control device performs image-capture control, which executes image-capturing of the target object with the camera a plurality of times when moving the working section with respect to the target object according to a predetermined trajectory, and focus control, in which predetermined images within a plurality of images captured by image-capture control are in focus.

Abstract: Data structure for image-processing data is for creating image-processing data necessary for performing image processing on captured images of multiple workpieces when an articulated robot extracts a workable target workpiece from among multiple supplied workpieces. The data structure includes workpiece shape data for recognizing a target workpiece by pattern matching and tool data configured to check whether there is interference between a tool mounted on the articulated robot and a peripheral workpiece. The data structure is configured such that the combination of the workpiece shape data and the tool data can be rearranged for each workpiece or for each tool.

Abstract: A work machine includes a pickup member configured to pick up a component; a storage device configured to store positional information on multiple pickup positions where the pickup member can pick up the component; a recognition device configured to optically recognize a multiple of the component including the pickup target; and a control device configured to select, from the multiple pickup positions of the pickup target component, one pickup position which is less likely to interfere with other components based on the positional information and a recognition result from the recognition device, and cause the pick member to pick up the pickup target component at the one selected pickup position.

Abstract: A robot system for performing drive control of a robot arm with respect to a target object according to information obtained by a camera, including a robot having a working section, a camera mounted in the vicinity of the working section, and a control device for controlling the driving of the robot while confirming the target object based on image data of the camera, is provided. The control device performs image-capture control, which executes image-capturing of the target object with the camera a plurality of times when moving the working section with respect to the target object according to a predetermined trajectory, and focus control, in which predetermined images within a plurality of images captured by image-capture control are in focus.