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: A seating state detection device includes an acquisition unit configured to acquire a detection signal group in a predetermined period that is output as a result of transmission and reception of waves by a radio wave sensor mounted on a vehicle, a signal extraction unit configured to extract specific-intensity signals in a predetermined reflection intensity range from the detection signal group, and a determination unit configured to determine whether an occupant in the vehicle is in a first riding state in which the occupant is directly seated on a seat or in a second riding state in which the occupant is seated in an infant auxiliary device, based on a distribution mode of the specific-intensity signals.

Abstract: An image display device configured to display, on a display screen, a predetermined image captured in a state in which multiple components to be mounted on a board are held by a mounting head, including: a display control section configured to selectably display, on the display screen, relevant information relating to the multiple components in association with each component, together with the predetermined image, and when a predetermined operation involving selection of any of the relevant information is performed by an operator, display an enlarged image of one component corresponding to the selected relevant information of the predetermined image being displayed.

Abstract: Provided is an image processing method for easily viewing images obtained by imaging multiple components at a time, the method including image capturing processing of capturing each component holding state relating to multiple suction nozzles mounted on a mounting head as one image, image dividing processing of dividing a region relating to a predetermined component holding state for image data of the multiple component holding states obtained by the image capturing processing, direction conversion processing of converting a direction of the component holding state for divided image data divided by the image dividing processing, and display processing of displaying an image based on the divided image data subjected to the direction conversion processing.

Abstract: An image display device configured to display, on a display screen, a predetermined image captured in a state in which multiple components to be mounted on a board are held by a mounting head, including: a display control section configured to selectably display, on the display screen, relevant information relating to the multiple components in association with each component, together with the predetermined image, and when a predetermined operation involving selection of any of the relevant information is performed by an operator, display an enlarged image of one component corresponding to the selected relevant information of the predetermined image being displayed.

Abstract: A component orientation determination data creation device for creating component orientation determination data used in a component orientation determination system that determines an orientation of the component by comparing a brightness value of a determination region specified in the component orientation determination data within an image of the component captured by a camera with a determination threshold. A difference image between an image of the component in a correct orientation and an image of the component in another orientation is calculated by acquiring multiple images of the component in different orientations by changing the orientation with respect to the camera of the component that is the target for the component orientation determination data creation.

Abstract: An abnormality of a gear is more appropriately predicted. An abnormality prediction device of the present disclosure is used in a feeding device including a driving section, a gear connected to the driving section, and a detection section configured to detect a position of a medium fed in accordance with driving of the gear, and intermittently feeding the medium. The abnormality prediction device acquires detection information regarding a feed amount of the medium based on the position of the medium detected over time by the detection section, decomposes the acquired detection information into a trend component regarding a moving average of the gear, a cycle component based on a cycle of the gear, and a random component obtained by excluding the trend component and the cycle component, obtains an abnormality level of the gear based on the cycle component obtained by the decomposition, and outputs the obtained abnormality level.

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 apparatus for performing work on a substrate includes an image processing device acquiring multiple images captured at different positions by performing imaging multiple times after a camera has been moved by a moving device such that a reference mark of a circuit board is within a range inside a field of view of the camera, creating a super resolution image using multi-frame super resolution processing, and recognizing the reference mark. The image processing device performs candidate region search processing of processing the image captured initially to search for a region within the image including a portion that has a possibility of being the reference mark as a candidate region after completion of the initial imaging, performs multi-frame super resolution processing on the candidate region after completion of final image capturing, creates a super resolution image of the candidate region, and recognizes the reference mark.

Abstract: Provided is an image processing method for easily viewing images obtained by imaging multiple components at a time, the method including image capturing processing of capturing each component holding state relating to multiple suction nozzles mounted on a mounting head as one image, image dividing processing of dividing a region relating to a predetermined component holding state for image data of the multiple component holding states obtained by the image capturing processing, direction conversion processing of converting a direction of the component holding state for divided image data divided by the image dividing processing, and display processing of displaying an image based on the divided image data subjected to the direction conversion processing.

Abstract: A mounting device sets a processing region for super-resolution processing based on an approximate position of a main body portion of a component included in a mark image for use in obtaining a position of a fiducial mark and then performs super-resolution processing. Thus, the processing region for super-resolution processing can be appropriately set and prevented from becoming larger than necessary with respect to the main body portion of the component. Further, the processing region for super-resolution processing is determined using the mark image captured under an imaging condition different from that for the component image for use in super-resolution processing. Thus, the processing region can be appropriately set while the component image is kept under an imaging condition suitable for super-resolution processing. Therefore, the processing region for performing super-resolution processing can be set more appropriately, and the super-resolution processing can be efficiently performed.

Abstract: A substrate working device including: an imaging device configured to image a substrate; a memory device configured to memorize various information; and an image processing device configured to perform, when specified work is performed with respect to multiple substrates, for a leading substrate, leading-substrate processing of performing imaging processing for detecting a specified detection target required for the specified work with respect to a leading image obtained by imaging the leading substrate using the imaging device, acquiring region information related to a region in the leading image in which the detection target was detected, and memorizing the region information in the memory device, and, for subsequent substrates except for the leading substrate, subsequent-substrate processing of setting a partial processing region in a subsequent image of the subsequent substrate captured by the imaging device based on the region information, and performing the image processing with respect to the set proce

Abstract: An apparatus for performing work on a substrate includes an image processing device acquiring multiple images captured at different positions by performing imaging multiple times after a camera has been moved by a moving device such that a reference mark of a circuit board is within a range inside a field of view of the camera, creating a super resolution image using multi-frame super resolution processing, and recognizing the reference mark. The image processing device performs candidate region search processing of processing the image captured initially to search for a region within the image including a portion that has a possibility of being the reference mark as a candidate region after completion of the initial imaging, performs multi-frame super resolution processing on the candidate region after completion of final image capturing, creates a super resolution image of the candidate region, and recognizes the reference mark.

Abstract: A substrate working device including: an imaging device configured to image a substrate; a memory device configured to memorize various information; and an image processing device configured to perform, when specified work is performed with respect to multiple substrates, for a leading substrate, leading-substrate processing of performing imaging processing for detecting a specified detection target required for the specified work with respect to a leading image obtained by imaging the leading substrate using the imaging device, acquiring region information related to a region in the leading image in which the detection target was detected, and memorizing the region information in the memory device, and, for subsequent substrates except for the leading substrate, subsequent-substrate processing of setting a partial processing region in a subsequent image of the subsequent substrate captured by the imaging device based on the region information, and performing the image processing with respect to the set proce

Abstract: An electronic component picked up and held by a mounting head of a component mounter is moved to an imaging position above a component imaging camera, the tip of the lead of the electronic component is imaged from below by the camera to acquire a lead image, and the lead image is inputted into an image recognition device configured from a neural network or the like and imaged processed so as to output the center position of the tip of the lead. Here, whenever an image processing error occurs, the lead image for which the image processing error occurred is displayed on a display device, and an operator specifies the center position of the tip of the lead in the lead image display on the display device and the specified center position is inputted into the image recognition device.

Abstract: A component mounting machine includes a part camera in which a suction nozzle for sucking a component P and a fiducial mark are provided on a head, a sub-lens is installed in a visual field of a lens, the component is imaged through a main lens, and it is possible to image the fiducial mark through the lens and the sub-lens. Distortion correction values of the main lens portion are measured, distortion correction values of the sub-lens portion are measured, and the distortion correction values are stored in advance as a distortion correction table. During component mounting, when the component P which is sucked by the suction nozzle and the fiducial mark are imaged at the same time by the part camera, the obtained image is corrected using the distortion correction table, and a suction state of the component P is detected based on the corrected image.

Abstract: Mounting device 11 captures an image of reference mark 25 at a first position at which mounting head 22 is stopped under first imaging conditions, and captures an image of component 60 under second imaging conditions. Then, mounting device 11 moves mounting head 22 and captures an image of reference mark 25 at a second position at which mounting head 22 is stopped under the first imaging conditions, and captures a second image of component 60 under the second imaging conditions. Further, mounting device 11 generates an image of component 60 picked up by mounting head 22 based on the positional relationship of reference mark 25 using the first image and the second image.

Abstract: A board production work method which includes a position detection process which detects an arrangement position of a detection target provided on a printed circuit board, and a work executing process which subjects the printed circuit board to predetermined production work based on the detected arrangement position, in which the position detection process includes an image acquisition step of imaging the printed circuit board under multiple imaging conditions and acquiring multiple items of original image data containing luminance values of each pixel arranged in two-dimensional coordinates, a difference calculation step of using two of the multiple items of original image data as calculation targets, calculating differences between luminance values of pixels with same coordinate values, and acquiring difference image data which is formed of luminance difference values of each of the pixels, and a position determination step of determining the arrangement position based on the difference image data.

Abstract: A mounting device sets a processing region for super-resolution processing based on an approximate position of a main body portion of a component included in a mark image for use in obtaining a position of a fiducial mark and then performs super-resolution processing. Thus, the processing region for super-resolution processing can be appropriately set and prevented from becoming larger than necessary with respect to the main body portion of the component. Further, the processing region for super-resolution processing is determined using the mark image captured under an imaging condition different from that for the component image for use in super-resolution processing. Thus, the processing region can be appropriately set while the component image is kept under an imaging condition suitable for super-resolution processing. Therefore, the processing region for performing super-resolution processing can be set more appropriately, and the super-resolution processing can be efficiently performed.

Abstract: A hybrid vehicle includes a generator to be driven by an internal combustion engine to generate an electric power. The internal combustion engine is to drive vehicle wheels via a hydraulic clutch. The electric power is to be supplied to an electric motor to drive the vehicle wheels. An oil pump is to be driven by the internal combustion engine to supply oil to the electric motor and the generator and to the hydraulic clutch. A valve is to decrease a first amount of the oil to be supplied to the electric motor and the generator and to increase a second amount of the oil to be supplied to the hydraulic clutch when the hydraulic clutch is in an engaged state. The valve is to increase the first amount of the oil and to decrease the second amount of the oil when the hydraulic clutch is in a disengaged state.