Abstract: The latest progresses in breast imaging using differential phase contrast techniques pose the question of how to fuse multiple information sources, yielded by absorption, differential phase, and scattering signals, into a single, informative image for clinical diagnosis. It is proposed to use an image fusion scheme based on a multiple-resolution framework. The three signals are first transformed into multiple bands presenting information at different frequencies and then a two-step processing follows: (1) intra-band processing enhances the local signal-to-noise ratio using a novel noise estimation method and context modeling; and (2) inter-band processing weights each band by considering their characteristics and contributions, and suppressing the global noise level. The fused image, looking similar to a conventional mammogram but with significantly enhanced detail features, is reconstructed by inverse transform.

Abstract: Provided is a method for processing a radiographic image including obtaining a radiographic image using an indirect radiographic detector comprising a scintillator panel and a pixel array panel, determining a parameter value for defining a point spread function (PSF) according to the scintillator panel or the pixel array panel, and correcting the radiographic image by deconvoluting the radiographic image using the PSF to which the parameter value is applied.

Abstract: Disclosed is a method for restoring a scan image. The method includes the steps of: measuring a blurring function oversampled with respect to a slit image obtained through a slit inclined at a predetermined angle in a vertical or horizontal direction according to the predetermined angle; and restoring a scan image to increase a resolution of an interface of a subject in the scan image obtained by obtaining the subject using the measured blurring function. Computed tomography (CT) that applies image restoration by increasing sampling can secure a precise image for computer-aided design (CAD)/computer-aided manufacturing (CAM) additionally used in a system used when actually diagnosing a patient, and thus does not require additional expenses and equipment.

Abstract: An image acquisition unit (2020) acquires an analysis image. The analysis image is an image in which a plurality of cell nuclei in a lesion of a target person are captured. A feature-value calculation unit (2040) calculates the feature-value relating to the cell nuclei from the analysis image. An evaluation function acquisition unit (2060) acquires an evaluation function from an evaluation function storage unit (10). The evaluation function is a function with which prediction information is calculated based on the feature-value. The prediction information generation unit (2080) generates prediction information relating to a target person based on a feature-value, which has been calculated from an analysis image, and an evaluation function which has been acquired by the evaluation function acquisition unit (2060). The prediction information is information indicating a prediction of a prognosis of a disease of the target person or a prediction of malignancy of a disease of the target person.

Abstract: Exterior orientation parameters of a camera are easily determined by, for example, a reference image being obtained by photographing a building 131 with a camera 112, in which exterior orientation parameters are determined, while a vehicle 100 travels, and a comparative image being simultaneously obtained by photographing the building 131 with a camera 113, in which exterior orientation parameters are undetermined. Then, points that match between the reference image and the comparative image are selected, and relative orientation and scale adjustment using a predetermined scale are performed, whereby the exterior orientation parameters of the camera 113 are calculated.

Abstract: A vision system of a vehicle includes a camera configured to be disposed at a vehicle so as to have a field of view exterior of the vehicle. The camera may include a fisheye lens. An image processor is operable to process image data captured by the camera. The vision system provides enhanced camera calibration using a monoview noncoplanar three dimensional calibration pattern. The system may include a plurality of cameras configured to be disposed at the vehicle so as to have respective fields of view exterior of the vehicle.

Abstract: An image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry selects from a plurality of diffusion-weighted images with different applied directions of a motion probing gradient magnetic field pulse or different diffusion sensitive coefficients, a diffusion-weighted image that conforms to a predetermined condition. The processing circuitry configured to register the selected diffusion-weighted image with a reference image for which the diffusion sensitive coefficient being set to a reference value to correct the selected diffusion-weighted image. The processing circuitry configured to register the corrected diffusion-weighted image with each of the other diffusion-weighted images of the plurality of diffusion-weighted images to correct each of the other diffusion-weighted images.

Abstract: A technique for foreground determination includes analyzing pixels that are deemed to be changing between frames, and applying a filtration technique that is based on fractal methods. Implementations include applying a filter that is designed to eliminate structures of dimensionality less than unity while preserving those of dimensionality unity and greater. The technique may be performed in real-time and makes use of a variable threshold for foreground determination and image segmentation techniques.

Abstract: An image processing method includes the steps of detecting edge information from an input image, identifying a plurality of lines from the edge information, dividing the input image into a plurality of areas based on the relative locations of the plurality of identified lines, calculating a similarity between adjacent areas of the plurality of divided areas, detecting boundaries between the adjacent areas as line segments partitioning the adjacent areas based on a degree of dissimilarity of the adjacent areas, wherein each of the line segments is at least a portion of the plurality of lines, and connecting the line segments forming the boundaries, and generating a connected shape using the boundaries.

Abstract: A system and method for multi-spectrum segmentation for computer vision is described. A first sensor captures an image within a first spectrum range and generates first sensor data. A second sensor captures an image within a second spectrum range different than the first spectrum range and generates second sensor data. A multi-spectrum segmentation module identifies a segmented portion of the image within the second spectrum range based on: the second sensor data, a subset of the first sensor data corresponding to the segmented portion of the image within the second spectrum range, and a segmented portion of the image at the second spectrum range corresponding to the subset of the first sensor data. The multi-spectrum segmentation module identifies a physical object in the segmented portion of the image within the second spectrum range, and a device generates augmented reality content based on the identified physical object.

Abstract: A cell tracking device includes first and second image acquisition units, first and second tracking units and an interpolation unit. The first image acquisition unit picks up images of a cell under a short-time exposure condition at points in time to capture short-time exposure images. The second image acquisition unit picks up images of the cell under a long-time exposure condition to capture long-time exposure images, each image of the cell under the long-time exposure condition being picked up within each interval between the points in time. The first tracking unit tracks the cell based upon the short-time exposure images. The second tracking unit tracks the cell based upon the long-time exposure images. The interpolation unit interpolates a tracking result obtained by the second tracking unit with a tracking result obtained by the first tracking unit.

Abstract: An image processing apparatus includes: an imaging distance estimating unit configured to estimate an imaging distance to a subject shown in an image; an examination region setting unit configured to set an examination region in the image such that an index indicating a spread of a distribution of imaging distances to the subject shown in the examination region is within a given range; and an abnormal structure identifying unit configured to identify whether or not a microstructure of the subject shown in the examination region is abnormal, by using texture feature data that enables identification of an abnormality in the microstructure of the subject shown in the examination region, the texture feature data being specified according the examination region.

Abstract: A stereo matching apparatus and method through learning a unary confidence and a pairwise confidence are provided. The stereo matching method may include learning a pairwise confidence representing a relationship between a current pixel and a neighboring pixel, determining a cost function of stereo matching based on the pairwise confidence, and performing stereo matching between a left image and a right image at a minimum cost using the cost function.

Abstract: Systems and methods for using geometric primitives to identify background in video data. In one embodiment, a method obtains video data depicting at least a portion of a user. The video data is processed with at least one persona identification module comprising a geometric primitive module for generating a first persona probability map at least in part by: detecting at least one geometric primitive within the video data; identifying a respective region within the video data associated with each of the at least one detected geometric primitives; and assigning the respective regions an increased background-probability in the first persona probability map; and outputting a persona image by extracting pixels from the video data based on the persona probability map.

Abstract: Among other things, one or more techniques and/or systems are described for correcting projection data generated from a computed tomography (CT) examination of an object and/or for computing or updating a CT value of the object from the projection data. An image generator is configured to generate a CT image of an object under examination. Using this CT image, a set of actions are performed to correct projection data from which the CT image was generated and/or to update a CT value of one or more voxels within the CT image. In this way, the projection data and/or CT image is adjusted to reduce image artifacts and/or otherwise improve image quality and/or object detection.

Abstract: A method and apparatus is provided to iteratively reconstruct a PET image for emission data using separable quadratic surrogates (SQS). The quadratic surrogates include a Poisson likelihood surrogate that has a curvature that depends on a back-projection of an inverse of mean-background signal. The method can be used with Nesterov acceleration and ordered subsets to achieve quadratic convergence to an image minimizing a Poisson Likelihood objective function that includes a regularizer that penalizes roughness in the reconstructed image.

Abstract: Computer-readable media, computer systems, and computing devices for method of providing spatial visualizations of metrics. In embodiments, the method includes referencing a spatial map having multiple spatial regions. A set of metric stacks is also referenced. The metric stacks graphically indicate values associated with multiple metrics. Further, each metric stack corresponds with one of the spatial regions based on location with which the values associated with the multiple metrics correspond. The metric stacks are overlaid on the corresponding spatial region within the spatial map such that a user can simultaneously view metrics associated with particular spatial regions.

Abstract: A branching and merging determination apparatus includes a recognizer and a determiner. The recognizer recognizes a target present in front of an own vehicle. The determiner determines, based on a result of the recognition of the target by the recognizer, presence or absence of branching and merging of roads. Specifically, the determiner is configured to: estimate a traveling section where branching or merging of roads is probably present; and determine that no branching or merging of roads is present in a region of the estimated traveling section where there is a preceding vehicle traveling at a higher speed than the own vehicle.

Abstract: A method including causing, at least in part, rendering of a perspective view showing one or more objects in a field of view. The method further including retrieving content associated with an object of the one or more objects in the field of view, and causing, at least in part, rendering of a graphic representation relating to the content on a surface of the object visible in the perspective view in a user interface for a location-based service of a mobile device.

Abstract: One embodiment of the present invention sets forth a technique for improving path rendering on computer systems with an available graphics processing unit. The technique involves reducing complex path objects to simpler geometric objects suitable for rendering on a graphics processing unit. The process involves a central processing unit “baking” a set of complex path rendering objects to generate a set of simpler graphics objects. A graphics processing unit then renders the simpler graphics objects. This division of processing load can advantageously yield higher overall rendering performance.

Abstract: In a tile-based graphics processing system, when a tile for a render output is to be generated, the fragment data storage requirements for each fragment to be generated for the tile is determined 51, and a color and/or depth buffer in the tile buffer is allocated for use by the fragments for the tile based on the determination 57. The graphics processing pipeline then, when generating rendered fragment data for the tile, stores the rendered fragment data in the color buffer and/or depth buffer of the tile buffer allocated to the fragments for the tile 58.

Abstract: The present application discloses a 3D model rendering method and apparatus and a terminal device. The method includes calculating, in a diffuse reflection illumination situation simulated by hardware, dot product operation results of a light vector and a normal line vector of each vertex on a surface of a 3D model, converting the dot product operation results of each vertex to corresponding UV coordinate values, then drawing, according to a preset correspondence between UV coordinate values and a color value of a 3D model basic texture after receiving light, a gradient map having a color value corresponding to the UV coordinate values of the each vertex, and covering the surface of the 3D model with the gradient map.

Abstract: According to one exemplary implementation, a method for use by a global illumination system including a hardware processor includes identifying, using the hardware processor, a first interior vertex of multiple first interior vertices of a light path, the first interior vertices being situated within a volume having a refractive boundary. In addition, the method includes determining, using the hardware processor, a surface vertex of the light path at the refractive boundary, and determining, using the hardware processor, a linear direction from the surface vertex to a light source of the light path. The method also includes determining, using the hardware processor, one or more second interior vertices for completing the light path by constructing a path from the surface vertex to the first interior vertex, based on the linear direction, the surface vertex and the first interior vertex.

Abstract: Data processing techniques are provided to increase a computational speed of iterative computations that are performed over a domain of data points, such as stencil computations. For example, a method includes loading a set of domain data points into a cache memory; obtaining an iteration count T, and a base stencil operator having a first set of coefficients; generating a convolved stencil operator having a second set of coefficients, wherein the convolved stencil operator is generated by convolving the base stencil operator with itself at least one time; and iteratively processing the set of domain data points in the cache memory using the convolved stencil operator no more than T/2 iterations to obtain final processing results. The final processing results are similar to processing results that would be obtained by iteratively processing the set of domain data points using the base stencil operator for the iteration count T.

Abstract: A system and method of deep learning using deep networks to predict new views from existing images may generate and improve models and representations from large-scale data. This system and method of deep learning may employ a deep architecture performing new view synthesis directly from pixels, trained from large numbers of posed image sets. A system employing this type of deep network may produce pixels of an unseen view based on pixels of neighboring views, lending itself to applications in graphics generation.

Abstract: Techniques are disclosed for suppressing access to a depth processing unit associated with a graphics processing pipeline. The method includes receiving a graphics primitive from a first pipeline stage associated with the graphics processing pipeline. The method further includes determining that the graphics primitive is visible over one or more graphics primitives previously rendered to a frame buffer, and determining that the depth buffer is in a read-only mode. The method further includes suppressing an operation to transmit the graphics primitive to the depth processing unit. One advantage of the disclosed technique is that power consumption is reduced within the GPU by avoiding unnecessary accesses to the depth processing unit.

Abstract: To integrate a sensory property such as occlusion, shadowing, reflection, etc. among physical and notional (e.g. virtual/augment) visual or other sensory content, providing an appearance of similar occlusion, shadowing, etc. in both models. A reference position, a physical data model representing physical entities, and a notional data model are created or accessed. A first sensory property from either data model is selected. A second sensory property is determined corresponding with the first sensory property, and notional sensory content is generated from the notional data model with the second sensory property applied thereto. The notional sensory content is outputted to the reference position with a see-through display. Consequently, notional entities may appear occluded by physical entities, physical entities may appear to cast shadows from notional light sources, etc.

Abstract: The power consumption of processor-based devices may be reduced by reducing the consumption of power during graphics processing. In some embodiments, the precision of pixel shading in parts of images where artifacts are less objectionable may be reduced. For example, in areas the user is not directly looking at, precision may be reduced to save power. At the same time, because a person is not focusing on those regions, even if usually perceptible artifacts occur because of the reduced precision, an overall pleasing depiction may be achieved.

Abstract: In one embodiment of the present invention, a foldable beam generator produces a foldable beam polyline that approximates a three-dimensional (3D) space curve. The foldable beam generator optimizes the number and position of joints included in the foldable beam polyline to minimize differences between the foldable beam polyline and the 3D space curve while complying with one or more manufacturing constraints. Notably, the foldable beam generator designs each of the joints to act as a living hinge that closes to a fixed angle when heated and solidifies when cooled. By using the foldable beam polyline as a 3D digital model for manufacturing and subsequently applying heat to assemble the manufactured 3D object, defects and/or limitations of complex 3D objects typically associated with traditional manufacturing techniques may be reduced. In particular, support structures designed to buttress three-dimensional (3D) digital models during 3D printing may be minimized.

Abstract: The present disclosure is directed toward systems and methods for providing a preview that includes a visualization of various properties of an object to be printed from a three-dimensional input model. For example, systems and methods described herein involve performing one or more of a printability analysis, appearance analysis, true-visual analysis, accuracy analysis, and an integrity analysis to identify defects, visual characteristics and other properties of the object to be printed. Systems and methods described herein further relate to generating texture maps and applying the texture maps to three-dimensional renderings of the three-dimensional model to provide an interactive preview to enable a user to view and comprehend various issues associated with printing the object from the three-dimensional model.

Abstract: A system and method for providing a fast, efficient and accurate method for recovery of depth information from a single image of a face is disclosed. The technique uses a novel thin-plate spline-based dense-correspondence method to align the face, and the representation incorporates a weighted framework, interpreting the depth recovery problem as a weighted data problem.

Abstract: The invention provides a system, apparatus and method for interactively displaying a virtual three dimensional structure representing building information modeling (BIM) data. The displaying of the virtual structure provides a viewing perspective that simulates both internal and external lighting effects upon the virtual structure. Commands being communicated by a viewer of the virtual structure are processed in real time to direct navigation (location and direction) of a virtual camera that is located within the virtual three dimensional structure.

Abstract: An example computer includes: an image acquiring unit that acquires an image of a real space captured by an imaging device; a feature detecting unit that detects a feature from the image; a determining unit that determines a virtual object, or, a virtual object and an aspect of the virtual object while changing the same in accordance with a recognition condition of the detected feature; an image generating unit that generates an image of a virtual space in which the determined virtual object or the virtual object in the determined aspect is placed on a basis of the feature; and a display controlling unit that displays an image on a display device such that the image of the virtual space is visually recognized by a user while being superimposed on the real space.

Abstract: Technologies are generally described for systems, devices and methods effective to set up image data to be processed by an augmented reality device. In some examples, a processor may generate image data from light reflected from a real object. The image data may represent, or may be a digital representation of, the real object. The processor may analyze a skin stack of augmented reality skins and identify one of the augmented reality skins stored in the memory. The augmented reality skin may include instructions effective to modify some of the image data when the image data includes a feature. The processor may create metadata related to the image data. The metadata may relate to the presence of the feature in the image data. The processor may store the metadata in the memory.

Abstract: An apparatus for estimating a camera pose includes an image acquisition unit to acquire a photographed image, a motion sensor to acquire motion information of the apparatus for estimating the camera pose, a static area detector to detect a static area of the photographed image based on the photographed image and the motion information, and a pose estimator to estimate a camera pose based on the detected static area.

Abstract: This invention solves the problem that objects in the field of view of reading glasses using multifocal lenses for correcting ocular refractive errors such as presbyopia appear distorted. This image display device is provided with the following: a distance computation unit that computes the distance to a subject in a field-of-view image; a visual-acuity-information acquisition unit that stores visual-acuity information for the user in advance; a corrected-image generation unit that generates and outputs a corrected image on the basis of the field-of-view image and an eye image generated from the field-of-view image, the distance information, and the visual-acuity information; and a display unit that displays the corrected image by superimposing same onto the user's field of view. Since the corrected image is superimposed without the use of lenses, lenses being the cause of the abovementioned distortion, the user can see close objects clearly.

Abstract: A head mounted display which allows a user to visually recognize a virtual image and external scenery, and includes an image display unit that forms the virtual image which is visually recognized by the user, and a superimposition processing unit that causes the image display unit to form the virtual image based on superimposition information for superimposing invisible information which is not shown in an appearance of an object on the object included in the external scenery.

Abstract: Providing of an electronic map displaying preferred real-world locations to utilize in connection with an augmented reality world. A request is received at a server computer to provide the electronic map to utilize in connection with the augmented reality world. A geolocation is received. Real-world locations in a vicinity are queried from a real-world location profile. A virtual location profile of virtual locations in the augmented reality world is accessed to generate an initial virtual location set. A participant preference profile containing virtual preferences and real-world preferences is accessed. Real-time participant data is accessed. The virtual locations in the initial virtual location set are prioritized to generate a prioritized virtual location set. The prioritized virtual location set is limited based upon the real-time participant data to generate a real-time prioritized location set. The electronic map is generated based upon the real-time prioritized location set, and transmitted.

Abstract: Disclosed is a method for hole-filling in 3D models. The method includes extracting static background information from a current frame of an input image and extracting virtual static background information using the static background information, warping a color image and a depth map of the current frame to acquire a virtual image and a virtual depth map, and labeling a hole area formed in the virtual depth map to extract local background information, performing a first hole-filling onto the virtual image and the virtual depth map using a similarity between the virtual static background information and the local background information, and performing a second hole-filling with respect to remaining holes after the first hole-filling in a manner of an exemplar-based in-painting method to which a priority function including a depth term is applied.

Abstract: The invention provides a structure self-adaptive 3D model editing method, which includes: given a 3D model library, clustering 3D models of same category according to structures; learning a design knowledge prior between components of 3D models in same group; learning a structure switching rule between 3D models in different groups; after user edits a 3D model component, determining a final group of the model according to inter-group design knowledge prior, and editing other components of the model according to intra-group design knowledge prior, so that the model as a whole satisfies design knowledge priors of a category of 3D models. Through editing few components by the user, other components of the model can be optimized automatically and the edited 3D model satisfying prior designs of the model library can be obtained. The invention can be applied to fields of 3D model editing and constructing, computer aided design etc.

Abstract: A method of inspecting a user device of a user of a transport system includes obtaining, by a portable inspection device, identification data of a user device of a user of a transport system; generating an inspection result of the user device, by an inspection system, in dependence on the read identification data and an item in a record within a database, wherein the record comprises a plurality of items each relating to entry data of a respective user device of a respective of users of the transport system; and conveying, by the portable inspection device, the result of the inspection.

Abstract: A respirator container includes a sealable chamber that is adapted to receive and contain a respirator having a unique identifying tag. The respirator container also includes a reader for reading the unique identifying tag of a respirator in the sealable chamber, and a timer for measuring the time during which a respirator is outside of the sealable chamber.

Abstract: Systems and methods are disclosed for determining whether or not a crash involving a vehicle has occurred. The acceleration of the vehicle may be measured using, for example, an accelerometer of a mobile device, which may be located inside the vehicle. The system may determine the magnitude of each accelerometer measurement and whether the magnitude exceeds one or more acceleration magnitude thresholds. The system may also determine the number of accelerometer events within a time window and whether the number exceeds one or more count thresholds. The system may determine whether a crash involving the vehicle has occurred based on the magnitudes of acceleration, number of acceleration events, and various thresholds. In some examples, the system may confirm that a crash has occurred based on, for example, the location of the mobile device.

Abstract: A method for determining a corrected yaw rate for a vehicle includes receiving a first yaw rate input from a yaw rate sensor of the vehicle and determining if the vehicle is moving or stationary. If the vehicle is determined to be moving, the method includes determining a steering angle of the vehicle, and determining an offset correction value based at least in part on a determined speed of the vehicle and the determined steering angle. A yaw rate offset is determined based at least in part on the determined offset correction value and the received first yaw rate input. A second yaw rate input is received from the yaw rate sensor of the vehicle, and a corrected yaw rate value is determined based at least in part on the received second yaw rate input and the determined yaw rate offset.

Abstract: Network buses in vehicles and other assets are monitored in order to obtain information and calculate alternate values of parameters relating to components connected to the bus and to send them to a management server. The device includes main code, which is common to the different vehicles or assets in a group, and a script, which is specific to each type of vehicle or asset. The script, which may be customizable, is responsible for defining the parameters to obtain and for defining how the values of the parameters are to be calculated. The script compensates for differences in the way different buses and components operate in different assets, which means that the values of like parameters obtained from different sources are all in conformance with each other. The script can be updated without interrupting the operation of the main code and the monitoring of the bus.

Abstract: A method and apparatus of performing a task on a system on a platform. A task script is received by a data processing system on the platform. The task script identifies task steps for performing the task on the system. The task script is run by the data processing system to perform the task on the system.

Abstract: A vehicle may include at least one operative sub-system that includes at least one sensor configured to output one or more sensor signals related to the at least one operative sub-system. A monitoring system is in communication with the operative sub-system(s). The monitoring system is configured to correlate the one or more sensor signals with respect to time, compile initial statistics of the one or more sensor signals with respect to a plurality of variables; and correlate the plurality of variables.

Abstract: Various embodiments relate generally to autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide an autonomous vehicle fleet as a service. In particular, a method may include receiving data associated with a sensor measurement of a perceived object, determining a label associated with the perceived object based on an initial calibration, retrieving log file data associated with the label, determining a calibration parameter associated with the sensor measurement based on the retrieved log file data, and storing the calibration parameter in association with a sensor associated with the sensor measurement. Sensors may be calibrated on the fly while the autonomous vehicle is in operation using one or more other sensors and/or fused data from multiple types of sensors.

Abstract: A vehicle having a decal attached thereto is provided herein. The vehicle includes a controller operably coupled with a powertrain of the vehicle and configured to calculate an energy efficiency performance score of the vehicle. A decal is disposed on the vehicle. One or more performance score indicators are disposed within the decal. A number of the one or more performance score indicators illuminate to represent the performance score.

Abstract: Disclosed are various embodiments for a data aggregation application. Operational data and image data may be captured from a client device. Odometer readings can be extracted from the image data. The operational data and image data can be verified by comparing an instrument panel depicted in the image data to a known instrument panel depiction.