Abstract: There is provided an item detection device that detects an item to be loaded and unloaded and includes an image acquisition unit acquiring a surrounding image obtained by capturing surroundings of the item detection device, an information image creation unit creating an information image, in which information related to a part to be loaded and unloaded in the item has been converted into an easily recognizable state, on the basis of the surrounding image, and a computing unit computing at least one of a position and a posture of the part to be loaded and unloaded on the basis of the information image.

Abstract: Systems and methods for identifying golf equipment. The system may include one or more performance tracking devices, such as an optical sensor system or a radar sensor system for tracking at least one of a golf club swing or a golf ball flight. The system also may include at least one processor and memory storing instructions that, when executed by the at least one processor, cause the system to perform a set of operations. The operations include receiving current dynamic input for a golf shot from a golfer and current static input for the golfer. The operations also include executing a trained machine-learning model based on the received current dynamic input and current static input to generate predicted golf club properties and/or predicted golf ball properties for the golfer. The predicted golf club properties and/or predicted golf ball properties are displayed on a connected display.

Abstract: Systems and methods for enhanced object detection for autonomous vehicles based on field of view. An example method includes obtaining an image from an image sensor of one or more image sensors positioned about a vehicle. A field of view for the image is determined, with the field of view being associated with a vanishing line. A crop portion corresponding to the field of view is generated from the image, with a remaining portion of the image being downsampled. Information associated with detected objects depicted in the image is outputted based on a convolutional neural network, with detecting objects being based on performing a forward pass through the convolutional neural network of the crop portion and the remaining portion.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: A method for the control of a robot assembly having at least one robot. The method includes acquiring pose data from an object arrangement having at least one object, which data has a first time interval; determining modified pose data from the object arrangement, which data has a second time interval that is larger or smaller than the first time interval, or is equal to the first time interval, on the basis of the acquired pose data; and controlling the robot assembly on the basis of said modified pose data.

Abstract: A method for measuring foot size and shape by using image processing includes a step of acquiring an image captured by simultaneously photographing a user's foot and an item having a standardized size; and a calculation step of calculating foot size or shape information from the image. The image is captured when at least a part of the user's foot comes in contact with the item.

Abstract: A calibration fixture that enables more accurate calibration of a touch probe on, for example, a CMM, with respect to the camera. The camera is mounted so that its optical axis is approximately or substantially parallel with the z-axis of the probe. The probe and workpiece are in relative motion, along a plane defined by orthogonal x and y axes, and optionally the z-axis and/or and rotation R about the z-axis. The calibration fixture is arranged to image from beneath the touch surface of the probe and, via a 180-degree prism structure, to transmit light from the probe touch point along the optical axis to the camera. Alternatively, two cameras respectively view the fiducial location relative to the CMM arm and the probe location when aligned on the fiducial. The fixture can define an integrated assembly with an optics block and a camera assembly.

Abstract: Systems and methods are described that probabilistically predict dynamic object behavior. In particular, in contrast to existing systems which attempt to predict object trajectories directly (e.g., directly predict a specific sequence of well-defined states), a probabilistic approach is instead leveraged that predicts discrete probability distributions over object state at each of a plurality of time steps. In one example, systems and methods predict future states of dynamic objects (e.g., pedestrians) such that an autonomous vehicle can plan safer actions/movement.

Abstract: Systems, methods, tangible non-transitory computer-readable media, and devices associated with motion flow estimation are provided. For example, scene data including representations of an environment over a first set of time intervals can be accessed. Extracted visual cues can be generated based on the representations and machine-learned feature extraction models. At least one of the machine-learned feature extraction models can be configured to generate a portion of the extracted visual cues based on a first set of the representations of the environment from a first perspective and a second set of the representations of the environment from a second perspective. The extracted visual cues can be encoded using energy functions. Three-dimensional motion estimates of object instances at time intervals subsequent to the first set of time intervals can be determined based on the energy functions and machine-learned inference models.

Abstract: Methods, systems, and devices for object detection are described. An example method for object detection is provided which may include capturing at least three polarization angles of a scene. The method may include translating polarization parameters associated with the at least three polarization angles to a reference angle to create a vector map and resolving the vector map into parallel components and perpendicular components, wherein the parallel components are parallel to a plane of incidence of light in the scene and the perpendicular components are perpendicular. The method may further include determining a range map based at least in part on the parallel and perpendicular components, detecting an object present in the scene using the range map and an airlight scattering polarization component, and outputting an indication of the object.

Abstract: A method and device for communication that is comprehensive among users, including receiving information concerning a first state transition in an autonomous driving system from a user of the autonomous driving system, determining information concerning a state of the autonomous driving system, based on the information concerning the first state transition and at least one second state transition, and saving the information concerning the state in at least one block chain. A method and device for communication in a user that is comprehensive among users, including determining a first state transition in the autonomous driving system based on information concerning a state of the autonomous driving system, information concerning at least one second state transition in the autonomous driving system being received from at least one block chain, and the state of the autonomous driving system being determined based on the information concerning the at least one second state transition.

Abstract: Localization error monitoring using vehicle state information is described. A computing system associated with a vehicle may determine a current state of the vehicle, such as a location, position, orientation, velocity, acceleration, or the like. The vehicle computing system may determine one or more metrics associated with the state of the vehicle. The metrics may include a variance associated with the state, a residual associated with a measurement corresponding to the state, or a correction factor applied to correct an input error. The computing system may determine whether the metric exceeds a threshold value. Based on a threshold exceedance, the computing system may determine one or more errors associated with a state of the vehicle. The vehicle computing system may control the vehicle based on the one or more errors.

Abstract: A method and device for digital measuring and ordering a custom orthopedic device includes an interactive method intended to assist clinicians select, measure and submit precise specifications for patients requiring custom orthopedic devices. The method includes a plurality of menus permitting the clinician to input specifications and submit orders electronically with the specifications and other data packaged together. The method and device include visualization indications to appropriately ensure image capture of a limb from various angles, including posterior, anterior, lateral and medial angles.

Abstract: A wearable apparatus for display glasses, according to certain embodiments, can include a display that includes a pair of screens configured to be mounted in front of respective eyes of a face of a wearer of the apparatus. The display can be configured to provide a display of information to the wearer. The information can include at least two options for selection. The wearable apparatus can also include a brain monitor configured to track brain wave activity of the wearer. The apparatus can further include a processor configured to identify one of the at least two options as selected based on the brain wave activity tracked by the brain monitor.

Abstract: The electronic device according to an embodiment includes: a camera; a display; a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: determine a size of a wall surface to be photographed to be output to an image display apparatus; control the display to display, on a preview image, a guideline indicating a region corresponding to the size of the wall surface to be photographed, based on a distance between the electronic device and the wall surface; control the camera to capture an image indicating the wall surface, based on the output guideline; and transmit the captured image to the image display apparatus such that the captured image is output to the image display apparatus.

Abstract: A system for a remotely controlled device to determine its location and orientation is disclosed. The system includes a remotely controlled device, at least one sensor connected to the remotely controlled device, the at least one sensor comprising a processor, and at least one emitter, wherein the at least one sensor is configured to receive the signal from the at least one emitter and the processor is configured to determine the location and orientation of the remotely controlled device.

Abstract: Presented herein are systems and methods for feature detection in images. A computing system may identify a biomedical image having features. The computing system may apply the biomedical image to a feature detection model. The feature detection model may include an encoder-decoder block to generate a feature map corresponding to the biomedical image, a confidence map generator having a second set of parameters to generate a confidence map using the feature map, and a localization map generator to generate a localization map using the feature map. The computing system may generate a resultant map based on the confidence map and the localization map. The resultant map identifying one or more points corresponding to the one or more features. The computing system may provide the one or more points identified in the resultant map for the biomedical image.

Abstract: Various embodiments are disclosed for simultaneous object localization and attribute classification using multitask deep neural networks. In an embodiment, a method comprises: obtaining, by a processing circuit, an image from an image capture device in an environment, the image including a target object in the environment; generating, by the processing circuit, predictions from the image for the target object using a multitask deep neural network, the multitask deep neural network including a network trunk and side branches, the network trunk configured for multi-scale feature extraction guided by supervision information provided by the side branches during training of the multitask deep neural network, the side branches configured as learning task-specific classifiers; and using, by the processing circuit, the predictions to localize the target object in the environment and to classify the target object and at least one attribute of the target object.

Abstract: An electronic device includes a measurement unit configured to measure a contour of a body by the electronic device being moved along a surface of the body and a controller configured to generate a three-dimensional image of the body based on the contour. The controller is configured to generate the three-dimensional image by lining up a plurality of first contours measured along a first direction.

Abstract: Systems and methods are provided for calibrating electromagnetic position tracking systems commonly used in virtual reality systems by compensating for steady state magnetic field distortions that can occur within a tracking volume and distort magnetic sensor readings. The calibration system includes a calibration device that holds magnetic sensor(s) in a fixed position relative to a reference position sensor object provided on the calibration device. The calibration data collection process includes positioning the calibration device at multiple locations within a tracking volume and measuring magnetic position readings using a magnetic tracking system and a corresponding reference position using the reference position tracking system.

Abstract: A method and system of virtual footwear try-on with improved occlusion processing are disclosed. The method comprises: capturing a foot image of a user; defining an ankle joint point in the foot image and defining at least one reference point according to the ankle joint point; capturing depth point data within a spatial range around the reference point and constructing an occlusion model according to the depth point data; positioning the occlusion model to a position corresponding to the foot image to obtain an occlusion processed image; positioning the footwear model on the occlusion processed image to produce a matching image of the footwear model and the foot; and hiding the occlusion model.

Abstract: In one embodiment, a method of machine learning and/or image processing for spectral object classification is described. In another embodiment, a device is described for using spectral object classification. Other embodiments are likewise described.

Abstract: The disclosure relates to a three-dimensional scanning system, the system comprises: a light source, configured to alternately project multiple speckle patterns and fringe patterns on the tested object in sequence; left and right cameras, configured to synchronously acquire left and right speckle images and left and right fringe images of the tested object; a speckle data and mark point data reconstruction module, configured to obtain three-dimensional speckle data and three-dimensional mark point data according to the speckle images; a fringe matching module, configured to back project the three-dimensional speckle data and the three-dimensional mark point data onto the left and right fringe images and guide fringes of the left and right fringe images for matching; and a three-dimensional reconstruction module, configured to reconstruct corresponding fringes matched with the left and right fringe images into the three-dimensional fringe point cloud data.

Abstract: The electronic device manufacturing apparatus includes a cable holding tool, a work stage, a robot section, a first position detector, a second position detector, and a controller. The first position detector detects positions in a two-dimensional plane direction of the cable held by the cable holding tool and the connector of the electronic device held by the work stage. The second position detector detects positions in a height direction of the cable held by the cable holding tool and the connector of the electronic device held by the work stage. The controller controls the robot section based on the detection result of the first position detector and the second position detector.

Abstract: The electronic device manufacturing apparatus includes a cable holding tool, a work stage, a robot section, a first position detector, a second position detector, and a controller. The first position detector detects positions in a two-dimensional plane direction of the cable held by the cable holding tool and the connector of the electronic device held by the work stage. The second position detector detects positions in a height direction of the cable held by the cable holding tool and the connector of the electronic device held by the work stage. The controller controls the robot section based on the detection result of the first position detector and the second position detector.

Abstract: The invention relates to a method for detecting the position of a mask holder for photolithographic masks, said method including the following steps: positioning the mask holder with the mask on a measuring table of a measurement apparatus, measuring the mask holder by use of an algorithm, storing the absolute position of the mask holder on the measuring table, and recording and storing at least one reference image.

Abstract: With the addition of directional information and gesture based input in a location based services environment, a variety of service(s) can be provided. For example, a computer system can identify a spatially-related point of interest based on a geographical location of the computer system and based on directional information. The computer system can display a first visualization of a first type, including an indication of the point of interest, which represents the geographical location. Then, based on detecting a gesture, the computer can display a second visualization of a second type, also including an indication of the point of interest, which also represents the geographical location.

Abstract: A system and method for markers with digitally encoded geographic coordinate information for use in an augmented reality (AR) system. The method provides accurate location information for registration of digital data and real world images within an AR system. The method includes automatically matching digital data within an AR system by utilizing a digitally encoded marker (DEM) containing world coordinate information system and mathematical offset of digital data and a viewing device. The method further includes encoding geographic coordinate information into markers (e.g., DEMs) and decoding the coordinate information into an AR system. Through use of the method and corresponding system, marker technology and the basis of geo-location technology can be combined into a geo-located marker, thereby solving the problem of providing accurate registration within an augmented reality.

Abstract: A wearable electronic device includes a headphone including two sound generators and an elastic band connecting the two sound generators; a display portion including two ends and a middle portion located between the two ends; and two extension mechanisms each of which connects one sound generator with a corresponding end of the display portion, a distance between the corresponding end of the display portion and the one sound generator being variable.

Abstract: A method for reducing an error rate is provided. The method includes obtaining a first analog signal representing a first kinematic property of a first position with a sensor, obtaining a second analog signal representing a second kinematic property of the first position, digitizing the first analog signal into a first digital signal, and digitizing the second analog signal into a second digital signal. The method also includes combining the first digital signal and the second digital signal into a combined signal such that an error rate of the combined signal is less than an error rate of one of the first digital signal and the second digital signal.

Abstract: A method for a computing device includes determining in a magnetometer, magnetic data in response to a physical perturbation, determining in an accelerometer, acceleration data in response to the physical perturbation, determining with a processor, computed parameters in response to the magnetic data and the acceleration data, wherein the computed parameters includes a first and a second computed parameter, determining with the processor, an initial motion direction indicator in response to a weighted combination of the first computed parameter and the second computed parameter, determining with the processor, a motion direction indicator in response to the initial motion direction indicator, determining with the processor, a function to perform in response to the motion direction indicator, and displaying on a display of the portable computing device with the processor, a graphic image in response to the function.

Abstract: There is provided an image processing device including: a setting unit configured to set a filter intensity based on a degree of how exactly an imaging device that produces a captured image containing a marker related to display of a virtual object faces the marker, the degree being detected based on the captured image; and an image processing unit configured to combine the virtual object corresponding to the marker with the captured image by using a filter having the set filter intensity.

Abstract: Systems and methods are provided for calculating point values for users who participate in activities. An activity is first captured with a sensor. A processor classifies the activity by comparing a sensor signal to templates. Once the activity is classified, an activity factor is selected. Point values are then calculated as a function of the activity factor and duration of the activity.

Abstract: An arrangement of loaded packages is estimated three-dimensionally. A loading position at which a target package is loaded next is determined based on the estimated arrangement. A position at which the target package is loaded is instructed by irradiation with an index light indicating the determined loading position. This method allows a package to be loaded in a limited space, for example, the package to be loaded optimally in a transport device or in a storehouse.

Abstract: A method for measuring a position using a magnet and a sensor for detecting the magnetic field strength of the magnet. The magnet and/or the sensor interact with a movable element so that a relative movement between the sensor and the magnet can be effected. The position of the movable element in accordance with the coordinates in a system of coordinates can be ascertained on the basis of the magnetic field having a predetermined shape generated by the magnet and detected by the sensor. The sensor ascertains three linearly independent spatial direction components of the magnetic field strength of the magnetic field acting at the location of the sensor. Each coordinate along a coordinate axis of the system coordinates of the magnetic field is determined individually and unambiguously by the combination of the three linearly independent spatial direction components of the magnetic field strength detected by the sensor.

Abstract: Systems and methods for implementing retail processes based on machine-readable images and user gestures are disclosed. According to an aspect, a method includes capturing one or more images including a machine-readable image and a user gesture. The method also includes identifying the machine-readable image as being associated with a product. Further, the method includes determining whether the user gesture interacts with the machine-readable image in accordance with a predetermined gesture. The method also includes implementing a predetermined retail process in association with the product in response to determining that the user gesture interacts with the machine-readable image in accordance with the predetermined gesture.

Abstract: There is provided a camera calibration device capable of highly precisely and easily estimating camera parameters without installing a piece of special calibration equipment or measuring 3D coordinates of reference points employed for calibration. A normal vector acquisition unit acquires normal vectors perpendicular to a reference horizontal plane from an image of a camera to be calibrated. A rotation matrix estimation unit projects the acquired normal vectors on a projection virtual plane perpendicular to the reference horizontal plane and evaluates that the projected normal vectors are perpendicular to the reference horizontal plane thereby to estimate a rotation matrix employed for calibrating the camera.

Abstract: There is provided a signal processing device comprising a combination unit (3) configured to combine plural element signals based on plural physical quantity signals including signal components in accordance with desired physical quantities, respectively, by the number of times equal to or greater than a number of the plural physical quantity signals, and to output combined signals different from each other; a measuring unit (4) configured to sequentially receive the combined signals output from the combination unit (3); and a computing unit (5) configured to compute signal components based on the desired physical quantities from signals that are generated based on the combined signals sequentially output from the measuring unit.

Abstract: A position and orientation measurement device includes a grayscale image input unit that inputs a grayscale image of an object, a distance image input unit that inputs a distance image of the object, an approximate position and orientation input unit that inputs an approximate position and orientation of the object with respect to the position and orientation measurement device, and a position and orientation calculator that updates the approximate position and orientation. The position and orientation calculator calculates a first position and orientation so that an object image on an image plane and a projection image of the three-dimensional shape model overlap each other, associates the three-dimensional shape model with the image features of the grayscale image and the distance image, and calculates a second position and orientation on the basis of a result of the association.

Abstract: One embodiment provides a method for use in a game that includes the steps of receiving position information for a controller that is being manipulated by a user, analyzing the position information to determine whether a predetermined movement of the controller associated with a command has been performed, and executing the command if the predetermined movement of the controller associated with the command has been performed.

Abstract: One embodiment provides a method for use in providing input to a system that includes the steps of determining position information for a controller for the system, comparing the determined position information for the controller with predetermined position information associated with commands, and providing a command to the system if the determined position information matches predetermined position information for the command.

Abstract: A three-dimensional measurement apparatus generates a plurality of view-point images obtained by observing a measurement object from a plurality of different view-points using a three-dimensional geometric model, detects edges of the measurement object from the plurality of view-point images as second edges, calculates respective reliabilities of first edges of the three-dimensional geometric model based on a result obtained when the second edges are associated with the first edges, weights each of the first edges based on the respective reliabilities, associates third edges detected from a captured image with the weighted first edges, and calculates a position and an orientation of the measurement object based on the association result.

Abstract: Various embodiments provide an input test tool that promotes precision testing, flexibility and repeatability over a wide variety of functionality tests that are utilized in both touch and near-touch input scenarios. The input test tool enables a variety of degrees of motion, including both linear and rotational motion, so that a device under test can be tested utilizing a number of different linear and/or rotational input scenarios.

Abstract: A method for processing data includes identifying a time signature of an infra-red (IR) beacon. Image data associated with the IR beacon is identified using the time signature.

Abstract: An adjustment device has a control unit with a memory, in which vehicle occupant data is storable. The data enable an automatic setting of all adjustable seat components and/or vehicle components. A read-in unit allows the necessary vehicle occupant data to be read into the memory of the control unit from a mobile data medium. The data medium obtains the necessary vehicle occupant data as a defined two dimensional image from a digital image acquisition system. The control unit or the data medium has an algorithm that determines proportions of given body parts in relation to each other from the two dimensional image such that a certain, at least relative, automatic setting of the seat components and/or the vehicle components is derivable. An input unit, which is manually operable as a touch screen, sets defined body part positions using marks superposed in succession on the image.

Abstract: A method and system for determining a location of a first device that emits a signal: provide at least three sensors separated and spaced apart from each other; at each of the sensors, receive the signal emitted by the first device; determine the received signals for each of the sensors; determine cross-correlations of the received signals for pairs of the sensors; and determine the location of the first device from the magnitudes of the cross-correlations of the received signals.

Abstract: In one example, a method includes determining, based on motion data generated by a motion sensor of a wearable computing device, a plurality of motion vectors, wherein one or more components operatively coupled to the wearable computing device are operating in a first power mode during a first time period; determining, based on the plurality of motion vectors, a plurality of values. In this example, the method also includes, responsive to determining that each of the plurality of values satisfies a corresponding threshold, transitioning, by at least one component of the one or more components, from operating in the first power mode to operating in a second power mode.

Abstract: A navigation system for use with moving vehicles includes target points proximate to a rendezvous site located on a first moving vehicle. One or more transmitters associated with the target points broadcast time-tagged target point positioning information. A navigation unit on a second moving vehicle utilizes a camera with known properties to capture images that include the target points. The navigation unit processes the image that corresponds in time to the positioning information, to determine the relative position and orientation of the rendezvous site at the second vehicle. The navigation unit utilizes the relative position and orientation and an absolute position and orientation of the rendezvous site calculated from the target position information and calculates an absolute position and orientation corresponding to the second vehicle.

Abstract: A machine tool includes a main axis 30 to which a touch probe 17 is attached, a motor 15 that rotationally drives the main axis 30, a rotation angle position detector 16 that detects a rotation angle position of the motor 15, and a control device 20. The control device, when a measurement mode command for performing measurement of a workpiece by the touch probe 17 is input, multiplies a d-axis current command value Idc by a d-axis current correction coefficient K that is less than 1 to reduce the d-axis current command value Idc to a d-axis current command correction value Idc?, using a d-axis current command correction section 4. Thus, in the machine tool, small rotation vibrations of the main axis, generated when rotating the main axis to which the probe is attached and performing measurements of a workpiece, can be suppressed to thereby increase the measurement accuracy.

Abstract: A non-destructive inspection system for a structure is described. The inspection system includes a local positioning system (LPS) configured for determining position and orientation of objects relative to a structure coordinate system, a six degree-of-freedom digitizer operable for at least one of temporary attachment to the structure and placement proximate the structure, a non-destructive sensor array, and a processing device.