Abstract: A control device is provided with a communication unit and a processing unit. The communication unit makes communication with a tool that is used for the work of fastening a fastener (for example, a screw) and with an image pickup unit for capturing an image of the work site where the work is being performed. The processing unit executes a determination process of determining whether or not the work is being performed normally on the basis of the fastening torque applied to the fastener by the tool and the image captured by the image pickup unit.

Abstract: The present invention relates to a method of producing a 3D centerline of an organ vessel from a plurality of 2D x-ray images. The method comprises the steps of producing a point-cloud of 3D points which represent intersecting and non-intersecting points between projection lines from the 2D images to their respective x-ray sources; fitting a compound curve to the points in the point-cloud of 3D points; removing outliers from the point-cloud; fitting a new compound curve to the remaining points in the point-cloud of 3D points; and repeating certain steps, wherein the resultant compound curve represents the 3D centerline of the organ vessel. The method minimizes reconstruction errors and produces an optimally-reconstructed 3D vessel skeleton.

Abstract: A location positioning device for a moving body acquires, via a communication device, a captured image from a camera in which an imaging direction has changed from a first direction to a second direction, the captured image including at least one marker disposed in space and at least one moving body that moves in the space, detects, based on the captured image and initial data, a change of the imaging direction from the first direction to the second direction, and acquires, based on the captured image, location data of the at least one moving body without returning the imaging direction of the camera in a real world to the first direction from the second direction.

Abstract: A framework for characterization of a collimator. In accordance with one aspect, first and second sides of the collimator are photographed to generate first and second image data. An optical characterization map (OCM) may be generated based on the first and second image data, wherein the optical characterization map characterizes the individual channels of the collimator. Quality assessment or image reconstruction may then be performed based on the OCM.

Abstract: A system and method of detecting an image of a template object in a captured image may include comparing, by a processor, an image model of an imaged template object to multiple locations, rotations, and scales in the captured image. The image model may be defined by multiple model base point sets derived from contours of the imaged template object, where each model base point set inclusive of a plurality of model base points that are positioned at corresponding locations associated with distinctive features of the imaged template object. Each corresponding model base point of the model base point sets may (i) be associated with respective layers and (ii) have an associated gradient vector. A determination may be made as to whether and where the image of the object described by the image model is located in the captured image.

Abstract: A card manufacturing system includes a locating device and a separation device. A laminate sheet comprising a plurality of cards is received by the locating device and is imaged using first and second imaging modalities. The first imaging modality identifies a location of each of the plurality of information carrying cards within the laminate sheet and the second imaging modality images at least one graphic formed on a surface of the laminate sheet. A position of the at least one graphic with respect to at least one information carrying card is determined and the plurality of cards are removed from the laminate sheet using information corresponding to the location of each of the plurality of information carrying cards when the position of the at least one graphic with respect to the information carrying cards is within a predetermined range.

Abstract: The invention relates to a method for inspecting a part mounted in a manufacturing fixture between two manufacturing operations by means comprising: a sensor a robot to hold and move the sensor a computer comprising memory means, computation means and display means, comprising in its memory means a three-dimensional digital model of the workpiece, and able to record the coordinates of the points acquired by the sensor the method comprising the steps consisting of: segmenting (1010) of the CAD model into a set of surfaces, designated as nodes, each node corresponding to a surface that is visible in a single acquisition according to the characteristics of the sensor determining (1020) the visibility of each node from each position of the sensor relative to said node determining common visibilities (1030) between the nodes.

Abstract: Image processing unit is provided in computer, and performs: for each of input images constituting a moving image obtained by capturing a workpiece during arc welding, a spatter detection step of detecting a spatter from an input image constituting a moving image of the workpiece, the moving image being generated by capturing the workpiece during the arc welding; a background bright spot identification step of identifying, as a background bright spot, a position in the moving image, the position being a position where a number of times of the detection in the spatter detection step is equal to or more than a predetermined reference number of times; and a spatter number identification step of identifying, for one input image, a number of spatters excluding spatters each corresponding to the background bright spot identified by the background bright spot identification step among the spatters detected by the spatter detection processing.

Abstract: A inspection method for a cylindrical honeycomb structure including a step of placing a cylindrical honeycomb structure made of ceramics on a rotation stage; a step of irradiating the side surface of the cylindrical honeycomb structure with light having a wavelength of 300 to 500 nm; a step of repeatedly capturing a reflected light from the side surface with a line sensor camera having a pixel resolution of 1 to 25 ?m/pix while the light is irradiated to the side surface and the cylindrical honeycomb structure is rotated around the axis of rotation, with a depth of field of the line sensor camera being adjusted to 0.5 to 5 mm; a step of generating an inspection image of the entire side surface; and a step of determining presence or absence of defects on the side surface based on the inspection image.

Abstract: A LIDAR sensor for an autonomous vehicle (AV) can include one or more lasers outputting one or more laser beams, one or more non-mechanical optical components to (i) receive the one or more laser beams, (ii) configure a field of view of the LIDAR sensor, and (iii) output modulated frequencies from the one or more laser beams, and one or more photodetectors to detect return signals based on the outputted modulated frequencies from the one or more laser beams.

Abstract: An end mill inspection device, which inspects an end mill having a blade part formed in a curved convex shape or an arc shape, includes: an imaging data acquisition unit that acquires imaging data obtained by capturing an image of a blade part of the end mill by an imaging unit; a contour extraction unit that extracts the contour of the blade part on the basis of the imaging data acquired by the imaging data acquisition unit; and a curvature radius calculation unit that calculates a curvature radius of the contour on the basis of the contour of the blade part extracted by the contour extraction unit.

Abstract: A hybrid computer/human method for generating, validating and using a ground truth map (GTM) provides for enforcement of data capture and transmission compliance of real and near real time video. Computer-implemented processes are used to identify and classify as allowed or disallowed objects in a local scene based on attributes of a video session. A human interface is available to validate either the object identification or classification. The GTM is then used, preferably in conjunction with motion sense, to enforce data capture and transmission compliance of real and near real time video within the local scene.

Abstract: Positions of both end edges of a weld bead in a bead width direction are measured over the entire circumference of a liner in a circumferential direction of the liner. Based on information on the position of the end edge, bead profile information being information on a shape of the end edge of the weld bead over the entire circumference of the liner in the circumferential direction is created. Based on this bead profile information, machining information of the liner per rotation of the liner being position information of a cutting tool in the bead width direction per phase in the circumferential direction of the liner is created so that a moving locus of the cutting tool relative to the liner along the circumferential direction of the liner approximates the shape of the end edge of the weld bead over the entire circumference of the liner in the circumferential direction.

Abstract: A system for tuning of axis control of a multi-axis machine and a method of operating the same are provided. The system includes a knowledge base for acquiring and maintaining factual knowledge associated with the tuning of the axis control. The factual knowledge has a uniform ontology a uniform data representation, and includes known input facts associated with known output facts. The system further includes an inference unit for automatically inferring new output facts associated with given new input facts in accordance with the factual knowledge.

Abstract: Embodiments of the present disclosure provide a method and a device for detecting defect of a meal box, a server, a device, and a storage medium. The method includes: receiving a detection request including an image of the meal box sent by a user terminal, the image of the meal box being obtained by an image acquirer of the user terminal; and performing defect recognition based on the image of the meal box and a defect detection model in response to the detection request.

Abstract: An assembly for acoustically influencing toothed wheels, including at least one first toothed wheel having teeth and one second toothed wheel having teeth, wherein the teeth have flanks, wherein at least one flank of a tooth of the first toothed wheel can be engaged with a flank of a tooth of the second toothed wheel, wherein at least one flank of a tooth of the first toothed wheel forms a contact zone or, in the ideal case, a contact line with an engaging flank of a tooth of a second toothed wheel, wherein the contact zone or the contact line is formed at an angle ?Aq, in particular between 5° and 85° or between 95° and 175°, in relation to an axis of an undulation, a microangle distribution, and/or a microangle periodicity of the engaging flank of the tooth of the second toothed wheel.

Abstract: A door access control system with a temperature detection function includes an infrared body temperature monitor device configured to detect a body temperature of a monitored object; a body temperature comparison device configured to compare a detected body temperature of the monitored object with a body temperature threshold; and a warning device configured to issue a warning message in response to the detected body temperature of the monitored object being higher than the body temperature threshold.

Abstract: A wear member monitoring system for a ground engaging tool, the system including: a measuring assembly having: an emitting device configured to emit a measurement signal towards a wear member of the ground engaging tool; a detecting device configured to detect a reflected measurement signal in response to the measurement signal emitted towards the wear member; and a processor configured to: analyse the reflected measurement signal with a two dimensional reference model; and determine a condition of the wear member based on the analysis of the reflected measurement signal with the two dimensional reference model.

Abstract: A method of inspecting an air data probe for damage or misalignment on a mounting surface includes retrieving reference data for the air data probe from a database, capturing images of the air data probe via a camera and generating dimensions from the captured images of the air data probe via a feature extractor. An alignment calculator analyzes the generated dimensions from the captured images of the air data probe and the reference data for the air data probe from the database to identify misalignment of the air data probe, and analyzes the generated dimensions from the captured images of the air data probe and the reference data for the air data probe from the database to identify damage of the air data probe. A maintenance recommendation for the air data probe is generated and outputted, based on the identified misalignment or damage of the air data probe.

Abstract: The described positional awareness techniques employing visual-inertial sensory data gathering and analysis hardware with reference to specific example implementations implement improvements in the use of sensors, techniques and hardware design that can enable specific embodiments to provide positional awareness to machines with improved speed and accuracy.

Abstract: According to one embodiment, a reading support system includes a processing device. The processing device includes an extractor and a type determiner. The extractor extracts a plurality of regions from a candidate region. The candidate region is a candidate of a region in which a meter is imaged. The regions respectively include a plurality of characters of the meter. The type determiner determines a type of the meter based on positions of the regions.

Abstract: Methods, systems and devices for inspecting workpieces are described. The method comprises acquiring partial measurement data from a plurality of workpieces associated with a batch of workpieces; composing an inspection data set from the partial measurement data; comparing the inspection data set to a reference data set defining tolerances for the workpieces; and accepting and rejecting the batch of workpieces based on the comparing of the inspection data set to the reference data set.

Abstract: The image inspection apparatus includes a camera that images a workpiece placed on a stage and generates a workpiece image, and a second camera having an imaging field-of-view wider than that of the camera, which images the workpiece and generates a bird's eye view image. The apparatus detects a position of the workpiece based on the bird's eye view image, and positions the workpiece based on the position of the workpiece so that the workpiece is located in or near an imaging field-of-view of the camera, thereby imaging the workpiece with the camera to generate the workpiece image. The apparatus specifies a detailed position and an orientation of the workpiece in the workpiece image generated by the camera, and determines an inspection point of the workpiece in the workpiece image based on the detailed position and the orientation of the workpiece specified, thereby executing a predetermined inspection process.

Abstract: Methods and systems for image analysis are provided, and in particular for identifying a set of base-calling locations in a flow cell for DNA sequencing. These include capturing flow cell images after each sequencing step performed on the flow cell, and identifying candidate cluster centers in at least one of the flow cell images. Intensities are determined for each candidate cluster center in a set of flow cell images. Purities are determined for each candidate cluster center based on the intensities. Each candidate cluster center with a purity greater than the purity of the surrounding candidate cluster centers within a distance threshold is added to a template set of base-calling locations.

Abstract: An image inspection device that determines a defect in an image of a surface to be inspected of a printed matter, based on a comparison between a captured image obtained by capturing the surface to be inspected and a master image includes a hardware processor that acquires the captured image and the master image, wherein the hardware processor: acquires region information about an image in a region having a predetermined area; specifies a processing technique of image alignment for each region in relation to the region information; executes at least an alignment process in relation to the region information as a process before the comparison by the specified alignment technique; and compares the captured image and the master image, on which the process before the comparison has been performed, and performs defect determination as to whether there is a defect in the captured image based on a comparison result.

Abstract: A control apparatus, comprising: an image obtaining unit configured to obtain an image in which a control target that a robot controls and a target position to which the control target is to be moved are imaged by an imaging apparatus that is attached to the robot; an axial direction obtainment unit configured to obtain an axial direction of a rotational axis of the control target; a target position detection unit configured to detect the target position in the image; an operation generation unit configured to generate an operation for the control target so that the target position is present in the axial direction and to further generate an operation by which the control target becomes closer to the target position in the axial direction; and a control unit configured to control the control target in accordance with the operation.

Abstract: A method of quantifying changes in a visceral organ comprises acquiring first (310) and second (410) medical scans of a visceral organ at first and second timepoints. At least part of the visceral organ in the first medical scan is parcellated into a first set of one or more subregions (420), based on image content, each subregion comprising a plurality of voxels. The first medical scan (310) is aligned to the second medical scan (410), before or after parcellating the first medical scan (310). Then the second medical scan is parcellated into a second set of one or more subregions. A metric is evaluated for a subregion in the first medical scan (310), and for the corresponding subregion in the second medical scan (410). A difference in the metric values provides a measure of a change that has occurred in the subregion, between the first and second timepoints.

Abstract: A method, system, and apparatus for a rivet measurement system for non-destructive testing measurements comprising a first measurement apparatus, a second measurement apparatus and a rivet analyzer. The first measurement apparatus acquires non-destructive testing measurements for sample production grade rivets of a particular class installed in a production vehicle structure. The second measurement apparatus acquires destructive testing measurements for the sample production grade rivets of the particular class.

Abstract: Various examples are provided related to face identification of material. An image can be captured by a vision system and feature parameters determined and compared to a material feature database to determine which face of the material is being presented. The vision system can employ a set of parameters for configuration to acquire the image. The system can communicate the identification to downstream processes in real time. A near-universal, color agnostic, angular orientation independent identification of material faces can be determined without the need for physical manipulation of the material.

Abstract: A method is disclosed. The method comprises defining a region of interest on a three-dimensional model of an object. The method may comprise capturing an image of an object manufactured according to the three-dimensional model. The method may comprise determining, using a processor, a position and orientation of the three-dimensional model with respect to the object in the captured image. The method may comprise locating the region of interest on the manufactured object. A portion of the manufactured object within the region of interest may comprise an identifiable feature. An apparatus and a machine-readable medium are also disclosed.

Abstract: An image capturing apparatus includes an image capturing portion, a controller to perform image processing to obtain a feature value from image data, and a storage device to accumulate the image data. In an image capturing period of capturing an image of the target object by the image capturing portion, the controller transmits a result of the image processing to a data management server while accumulating the captured image data the storage device, while in an image capturing suspension period of not performing image capturing, the controller transmits the image data accumulated in the storage device to the data management server.

Abstract: An information processing device is an information processing device configured to be used in a processing system including a processing device configured to perform predetermined processing on a three-dimensional processing target, the information processing device including: a control section configured to acquire 3D data of the processing target; display the processing target on a three-dimensional object display screen in a three-dimensional shape, being capable of being moved, rotated, scaled up, and scaled down, based on the acquired 3D data; acquire designation information of a position on a surface of the processing target; and output positional inclination information based on the 3D data, the positional inclination information including information relating to a coordinate of the position and an inclination of the surface of the processing target corresponding to the acquired designation information.

Abstract: The techniques described herein relate to methods, apparatus, and computer readable media configured to encode and/or decode video data. Point cloud video data is received that includes metadata specifying one or more regions of interest of the point cloud video data. A first region of interest is determined from the one or more regions of interest. A portion of the point cloud video data associated with the first region of interest is determined. Point cloud media is generated for viewing by a user based on the determined portion of the point cloud video data associated with the first region of interest.

Abstract: Disclosed aircraft wing-to-body join methods include measuring a 3D surface contour of each wing root interface surface of a wing root to form a complete wing root 3D surface profile; measuring a 3D surface contour of each wing stub interface surface of a wing stub to form a complete wing stub 3D surface profile; calculating a virtual fit between the aircraft wing and the aircraft body assembly that defines one or more gaps between the wing root interface surface and the wing stub interface surface; and aligning the aircraft wing to the aircraft body assembly to achieve a real fit consistent with the virtual fit.

Abstract: The invention relates to a folding machine for folding an object, using a measurement system for measuring an angle between a first plane through a first surface area and a second plane through a second surface area of an object. The system includes a sensor arrangement for measuring the coordinates in a measurement coordinate system of a plurality of measurement spots in the first surface area, and an inclinometer for measuring an inclination of the measurement coordinate system to the direction opposite to the direction of the force of gravity. The measurement system also includes a processing device for determining the angle between the first plane and the second plane based on the measured coordinates of the plurality of measurement spots, the measured inclination and information on the angle between the second plane and the direction opposite to the force of gravity.

Abstract: A similar damage search device includes a database that stores first damage information generated on the basis of a damage image of a structure, the first damage information including a damage vector obtained by vectorizing damage of the structure, and damage structure information including at least one of information on a hierarchical structure of the damage vector or information on a direction of the damage vector, an information acquisition unit that acquires second damage information corresponding to the first damage information on the basis of a damage image of a search target; and a search unit that searches for one or a plurality of pieces of first damage information similar to the second damage information from among the first damage information stored in the database on the basis of the second damage information acquired by the information acquisition unit.

Abstract: Described is a computer-implemented method for recognizing the geometry of a portion of an object in a digital representation of the object having a plurality of image points representing at least one material interface of the object. The method comprises determining and displaying the object representation, receiving a user input specifying a first position in the object representation as a starting point, determining a first set of image points in the vicinity of the starting point representing the geometry of the portion of the starting point, determining a checking geometry on the basis of the first set of image points by adapting at least one geometry element to the first set of image points, determining a second set of image points in the vicinity of the starting point representing the geometry of the portion of the checking geometry, inserting the second set of image points into and displaying a target set of image points.

Abstract: Sequence data, such as time series data is analyzed using neural networks, for example, recurrent neural networks. The sequence data is obtained from a source. For example, a sequence data may represent time series data obtained from a sensor. As another example, the sequence of data may represent a sequence of user interactions performed by a user with an online system. The sequences of data are provided as input to a neural network. A feature vector representation of each input sequence data is extracted from the neural network. The feature vector representation is used for clustering the sequence data. Salient features of clusters of sequence data are determined. The salient features of clusters of sequence data are provided for display via a user interface.

Abstract: A system and method for generating models from digital images in an interactive environment comprising a memory and a processor in communication with the memory. The processor captures or derives metadata for one or more digital images. The processor derives transforms from the metadata to align the digital images with one or more three-dimensional (“3D”) models of objects/structures represented in the digital image. The processor generates an interactive environment which allows a user to view a contextual model of each of the objects/structures in two dimensional (“2D”) and 3D views.

Abstract: An image processing device (400), comprising an image input interface (402) configured to receive input pixel values allocated to pixels in a two-dimensional pixel grid, a marker input interface (404) configured to receive marker position data indicative of a position of a marker within the pixel grid, and a marker position refining unit (406) configured to identify, using the pixel data and the marker position data, a target pixel having a highest symmetry value, i.e. identification value, which has been determined based on weighed symmetry values of the pixels within a search region that includes the marker position, and to determine a refined marker position data as the position data of the target pixel.

Abstract: A method for robotic inspection of a part, includes the steps of: supporting the part with a robot mechanism; obtaining part-related sensor input with a sensor positioned to inspect the part supported by the robot mechanism; and controlling movement of the robot mechanism relative to the sensor, wherein the controlling is done by a feedback control unit which receives the sensor input, and the feedback control unit is configured to control the robot mechanism based upon the sensor input.

Abstract: Provided are a crack information detection device, a method of detecting crack information, and a crack information detection program capable of accumulating a manual editing history with respect to an automatically detected damage to improve detection accuracy of a crack. It is assumed that a delete flag “1” of a damage vector (C5-2) is recorded in hierarchical structure information by completion of a delete operation with respect to the damage vector (C5-2). In the case, in a case where the number of operations or an operation time required for the completion of the delete operation is equal to or larger than a predetermined threshold value (for example, click ten times or more, drag and drop five times or more, or ten minutes or more from the start to the end of the editing operation), threshold values of an angle ?1 and an angle ?2 are reduced by a predetermined amount.

Abstract: A method of performing person re-identification for images captured by at least two camera pairs operating with different environmental factors. Descriptors representing characteristics of objects corresponding to a person in the images are clustered. A probability distribution of the clustered descriptors is determined. A coupling map for the images is determined based on the probability distribution. A cross-correlation between at least two of the coupling maps is determined. A similarity of the images captured by the camera pairs is determined according to the cross-correlation. Person re-identification is performed for the different environmental factors using the descriptors, based on the determined similarity.

Abstract: An endoscope device includes an imaging unit and an operation unit that is configured to receive results of an assessment on an endoscopic image of an object as captured by the imaging unit. A retrieval control unit is configured to retrieve one of assessment assist images stored in a data accumulation unit based on information on the assessment results. A display control unit is configured to display the retrieved one assessment assist image along with the endoscopic image on a display unit.

Abstract: In a setting mode, a processor stores in a memory a reference image and reference imaging position information indicating an imaging position of the reference image. In a measurement mode, the processor drives at least one of a table and an imaging section by a driving section according to the reference imaging position information stored in the memory to move an imaging position of the imaging section to the imaging position of the reference image and execute a pattern search.

Abstract: A method for quantitatively measuring internal defects in an as-cast steel product includes optically scanning at least a portion of a surface of the steel product with a scanning device to create a digital image thereof, analyzing the digital image to calculate a quantitative value for an amount of internal defects therein, and normalizing the quantitative value to a rating according to a standardized scale.

Abstract: A hierarchical structure information generation unit 112 corrects hierarchical structure information based on an editing instruction input by a user through an operation unit (120) (step S160: editing step). A display of the hierarchical structure information is updated based on the editing instruction input. The editing instruction input includes deleting a damage vector corresponding to a randomly selected label, combining a plurality of discontinuous damage vectors associated with a plurality of randomly selected labels into one continuous damage vector, releasing the combination between the plurality of the damage vectors, and selection of a label corresponding to a vector group, and deletion, combination, and release of the combination of the vector group corresponding to the selected label.

Abstract: A computer-implemented method comprises: receiving, by a computing device, sensor data associated with a geographic location; processing, by the computing device, the sensor data to identify an infrastructure asset within the geographic location; performing, by the computing device, a preliminary damage assessment of the infrastructure asset based on processing the sensor data; and storing or outputting, by the computing device, information regarding the preliminary damage assessment.

Abstract: Systems and methods are provided relating to artificial neural networks are provided. The systems and methods obtain a teacher network that includes artificial neural layers configured to automatically identify one or more objects in an image examined by the artificial neural layers, receive a set of task images at the teacher network, examine the set of task images with the teacher network, identify a subset of the artificial neural layers that are utilized during examination of the set of task images with the teacher network, and define a student network based on the set of task images. The student network is configured to automatically identify one or more objects in an image examined by the subset.

Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.