Abstract: A system and method of detecting, quantifying, and characterizing corrosion and degradation of an article, includes receiving signals indicative of a stack of images of a surface of the article; determining depth and nature of features in the stack of images; generating a surface model of the article in response to the determination of the depth and the nature of features; determining features of interest from the surface model; comparing the features of interest with predetermined information on the article; and characterizing the article as corroded or degraded in response to the comparisons of the features of interest.

Abstract: Examples disclosed herein relate to calibrating a device based on intrinsic parameter value selection and a projected calibration target. A process may calibrate a camera and/or device by creating 3D calibration information for a device, such as a camera or projector, based on a set of intrinsic calibration intrinsic parameter value options, a calibration target of known dimensions, and a virtual calibration target created based on an image captured by the camera of a projection by the projector onto the calibration target.

Abstract: Systems and methods are disclosed for estimating aesthetic quality of digital images using deep learning. In particular, the disclosed systems and methods describe training a neural network to generate an aesthetic quality score digital images. In particular, the neural network includes a training structure that compares relative rankings of pairs of training images to accurately predict a relative ranking of a digital image. Additionally, in training the neural network, an image rating system can utilize content-aware and user-aware sampling techniques to identify pairs of training images that have similar content and/or that have been rated by the same or different users. Using content-aware and user-aware sampling techniques, the neural network can be trained to accurately predict aesthetic quality ratings that reflect subjective opinions of most users as well as provide aesthetic scores for digital images that represent the wide spectrum of aesthetic preferences of various users.

Abstract: The present invention discloses a method for retrieving atmospheric aerosol based on statistical segmentation. Firstly a multi-band remote sensing image including an apparent reflectance and an aerosol optical thickness look-up table corresponding to a retrieval band is obtained, then pixels are partitioned and screened according to apparent reflectance segments of a mid-infrared 2.1 micrometer band. After that the retained pixel sets are further partitioned and screened according to the apparent reflectance segments of the mid-infrared 1.6 micrometer band. Finally the obtained pixel sets are partitioned into two categories according to the pixel number, one category including pixels having more pixels, the other including those with less pixels. The category with more pixels is taken as the reference part for retrieval.

Abstract: A design aware system, method, and computer program product are provided for detecting overlay-related defects in multi-patterned fabricated devices. In use, a design of a multi-patterned fabricated device is received by a computer system. Then, the computer system automatically determines from the design one or more areas of the design that are prone to causing overlay errors. Further, an indication of the determined one or more areas is output by the computer system to an inspection system for use in inspecting a multi-patterned device fabricated in accordance with the design.

Abstract: A method of thermographic nondestructive evaluation may include heating a portion of a surface of an object from a first surface temperature to a second surface temperature that is greater than the first surface temperature, collecting a plurality of thermal images of the portion of the surface of the object, detecting the sound zone of the portion of the surface of the object, determining a characteristic time corresponding to a time after the heating of the portion of the surface of the object wherein the sound zone of the surface of the object approaches a steady state temperature, normalizing temperature data of the plurality of thermal images with respect to the characteristic time and the steady state temperature, and detecting the defect zone based on differences between normalized temperature data of pixels of the defect zone and normalized temperature data of pixels of the sound.

Abstract: An image processing apparatus includes a computer system comprising an image acquiring section that acquires an image of body tissue. An extracting section of the computer system extracts an outline of the body tissue from the image, and a converting section of the computer system converts a coordinate sequence of the outline into a value sequence. An estimating section of the computer system estimates an abnormal shape of the body tissue by performing neural network processing on the value sequence. In addition, present invention embodiments include a computer program product used by the image processing apparatus and an image processing method performed by the image processing apparatus.

Abstract: A five-index quantitative analysis of OCT angiograms is disclosed. One method of analyzing an anatomical region of interest of a subject includes acquiring vascular image data from the region of interest and generating a binary vasculature map from the vascular image data. A vessel skeleton map and vessel perimeter map are generated from the binary vasculature map. Based on the three generated maps, a vessel area density, vessel skeleton density, vessel perimeter index, vessel diameter index, and vessel complexity can be determined, in addition to detection of any flow impairment zones in the region of interest. These metrics can be used to detect and assess vascular abnormalities from multiple perspectives.

Abstract: An apparatus for processing a computed tomography (CT) image includes a processor configured to set window widths and window levels of a plurality of setting areas, and a display configured to display a screen view showing a plurality of CT images on the plurality of setting areas, wherein the plurality of setting areas have different window levels. The window widths are portions of a display range of the display, and the window lengths are midpoints of the portions of the display range of the display. The processor generates and converts the CT images according to the window widths and the window levels.

Abstract: Systems and methods for analyzing vessels in multiplexed images include detecting large vessels using a spoke feature detection method, detecting long and narrow vessels using a line feature detection method, detecting smaller vessels using rolling-ball filtering and binary image operations to generate a mask, and evaluating any contour polygons resulting from these operations using quality measurements and other thresholds. Maturity determination and nuclei detection are also performed, resulting in an output of vessel characteristics and co-locations enabling enhanced analysis of multispectral images.

Abstract: A method for using an assembled three-dimensional image to construct a three-dimensional model for determining a path through a lumen network to a target. The three-dimensional model is automatically registered to an actual location of a probe by tracking and recording the positions of the probe and continually adjusting the registration between the model and a display of the probe position. The registration algorithm becomes dynamic (elastic) as the probe approaches smaller lumens in the periphery of the network where movement has a bigger impact on the registration between the model and the probe display.

Abstract: A device and method of determining proper positioning of lifeguard stations at a swimming pool to minimize the risk of bather drowning. The method includes: positioning submersible devices or other objects at the bottom of a swimming pool according to an established grid or pattern; imaging the devices from different locations and different heights at the same locations; analyzing the images to determine the position and height of the locations which provide the best sightlines of the swimming pool from the surface of the water to the bottom of the pool shell; and positioning the lifeguard stations at the position and height of the locations determined by analyzing the images.

Abstract: A system for determining a camera pose relative to an object including a unique feature may include a monocular camera configured to produce an image of the object, and a processing unit in operative communication with the monocular camera. The processing unit may be configured to: identify the unique feature of the object in the image produced by the monocular camera, synthesize at least four points along a contour of the object in the image using the identified unique feature as a starting point, synthesize a same number of points as synthesized in the image along a contour of the object in a reference model, the reference model preprogrammed into a memory of the processing unit, correlate the points from the reference model to the image, and determine a pose of the monocular camera based on the correlated points.

Abstract: Disclosed are a depth refinement system and a method for a sparse depth image in a multi-aperture camera. The method includes providing a sparse depth map generated based on an image obtained through each of a plurality of apertures included in the multi-aperture camera, wherein the sparse depth map includes depths of pixels included in the image, and performing a depth noise reduction (DNR) based on the sparse depth map.

Abstract: A simulation apparatus may comprise: a sensor unit configured to acquire movement information of an object using one or more sensors; a direction calculation unit configured to calculate direction information of the object using the movement information; and a simulation unit configured to simulate a physical object and render an image of the physical object on the basis of the direction information received from the direction calculation unit. The direction calculation unit may include a time delay correction unit configured to correct the direction information using a time difference between the time of acquiring the movement information and the time of rendering the image.

Abstract: Estimation techniques for vision-aided inertial navigation are described. In one example, a vision-aided inertial navigation system (VINS) comprises an image source to produce image data for a keyframe and one or more non-keyframes along a trajectory, the one or more non-keyframes preceding the keyframe along the trajectory. The VINS comprises an inertial measurement unit (IMU) to produce IMU data indicative of a motion of the VINS along the trajectory for the keyframe and the one or more non-keyframes, and a processing unit comprising an estimator that processes the IMU data and the image data to compute state estimates of the VINS. The estimator computes the state estimates of the VINS for the keyframe by constraining the state estimates based on the IMU data and the image data for the one or more non-keyframes of the VINS without computing state estimates of the VINS for the one or more non-keyframes.

Abstract: A method of predicting warps for image registration includes receiving warp data for a first band pair in an N-band system. The method includes fitting a warp model to the warp data to produce an offset profile for the first band pair, predicting a respective offset profile for at least one other band pair in the N-band system, and using the predicted respective offset profile to generate a warp for the at least one other band pair. The method also includes registering images of the at least one other band pair using the warp for the at least one other band pair. In another aspect, a method of predicting warps for image registration includes receiving warp data for m band pairs in an N-band system, wherein m?(N?1) and m>2, to register images.

Abstract: A method for determining an extent of anistropy of texture of an image in a manner that avoids inaccuracies arising from interpolation.

Abstract: Provided herein is a method for generating a road surface. The method for generating a road surface includes: obtaining a view height of a laser scanner used in an operation process through a mobile mapping system (MMS); determining a reference height on the basis of the obtained view height and a height measured by a global positioning system (GPS); extracting point cloud data positioned in a predetermined height range from the determined reference height among point cloud data obtained in the mobile mapping system; and generating the road surface on the basis of the extracted point cloud data.

Abstract: Disclosed is a method and system for processing images from an aerial imaging device. An image of an object of interest is received from the aerial imaging device. A parameter vector is extracted from the image. Image analysis is performed on the image to determine a height and a width of the object of interest. Idealized images of the object of interest are generated using the extracted parameter vector, the determined height, and the determined width of the object of interest. Each idealized image corresponds to a distinct filled volume of the object of interest. The received image of the object of interest is matched to each idealized image to determine a filled volume of the object of interest. Information corresponding to the determined filled volume of the object of interest is transmitted to a user device.

Abstract: A method for tracking an object in an image sequence with at least a first image and a second image includes the steps of: identifying a plurality of objects in the first image and a plurality of objects in the second image; determining matching probability of an object in the second image with an object in the first image, based on relative positional relationships between the plurality of objects in the first image and relative positional relationships between the plurality of objects in the second image; and determining, based on the determined matching probability, a matching result relating to whether the object in the second image matches with the object in the first image. A match indicates that the object in the second image corresponds with or originates from the corresponding object in the first image.

Abstract: Provided is an apparatus for recognizing user postures. The apparatus recognizes detailed postures such as a stand posture, a bending forward posture, a bending knees posture, a tilt right posture, and a tilt left posture, based on a variation between body information at a previous time and body information at a current time.

Abstract: Certain embodiments may relate to presenting imagery within a virtualized environment. A method and apparatus may be provided. The method may include generating a virtualized environment for a user. The method may also include detecting an object in the real world. The method may further include rendering imagery corresponding to the detected object in the virtualized environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enhancing skin tone in a ghost image are disclosed. In one aspect, a method includes the actions of receiving a color image. The actions further include converting the color image to a grayscale image. The actions further include generating a foreground image by removing background pixels from the grayscale image. The actions further include determining a foreground pixel value range of the pixel values of the foreground image. The actions further include generating a transfer function based on the foreground pixel value range, a minimum pixel value, and a maximum pixel value. The actions further include generating a transferred image by applying the transfer function to each pixel of the foreground image. The actions further include generating a monochrome image of the transferred image.

Abstract: A system for creating and rendering a color gradient field. The system includes a computer input device, a tangible computer-accessible storage medium, a processor coupled to the storage medium and a gradient stack editor. The editor creates a gradient stack data structure that includes a gradient paths, each path having a plurality of color and or opacity control points. Each path has a relative position within the gradient field. The data structure also has a secondary path extending into the gradient field. The gradient stack editor also includes a plurality of effect tools that cause the processor to receive and store information to the gradient stack data structure and the information is indicative of gradient path attributes and color and or opacity control point attributes. A gradient stack tool causes the processor to apply a gradient definition to the data of the gradient stack and to create a graphic document usable by an effect renderer.

Abstract: An apparatus for use in medical imaging, includes: an imager configured to receive radiation, and to generate electrical signals in response to the received radiation, wherein the imager comprises imaging elements; and a processing unit configured to generate a video, wherein the video comprises a first image having a first image resolution and a second image having a second image resolution that is different from the first image, the first image and the second image generated using the imager.

Abstract: A method and apparatus is provided to predict a regularization parameter for regularized iterative reconstruction of radiation detection data (e.g., computed tomography (CT) data or positron-emission tomography (PET) data) to generate a reconstructed image having specified statistical properties. The predicted regularization parameter is determined using a root-finding method performed on a transcendental objective function. The objective function is calculated using a three-dimensional Fourier transforms of an approximation to a shift invariant Hessian matrix and of matrix products between the forward-projection and back projection matrices of the system model and various (statistical) weight matrices. The specified statistical properties can include the standard deviation within a region of interest, a local spatial resolution, a low-contrast-detectability metric, etc.

Abstract: In a method and medical imaging apparatus for depiction of medical imaging data, medical imaging data of the examination object are acquired over a period of time, and an artifact parameter is established, which characterizes artifacts that occur as a result of breathing of the examination object during the period of time. The medical imaging data are displayed on a display screen together with a depiction of the artifact parameter.

Abstract: A system including at least one apparatus creates a representation of a road geometry from a plurality of sets of data, each set of data including at least an indication of a position and an indication of a heading of a mobile object. The system detects an intersection in the representation of the road geometry. The system defines at least one Bézier curve representing a trajectory between an entry to and an exit from the intersection. The system replaces at least a part of the created representation of the road geometry for the intersection by the at least one defined Bézier curve.

Abstract: Embodiments described herein relate generally to apparatuses and methods for structuring and processing data. In some embodiments, a method includes receiving stimulus-response data, via a processor, the stimulus-response data including a digital representation of a stimulus and a digital representation of a response. The processor calculates a weight associated with the stimulus-response data, based on a rule, and identifies: (1) a distribution type, based on the digital representation of the stimulus; and (2) a range of inclination values of the distribution type, based on the digital representation of the response. The processor compiles a compressed multidimensional data profile associated with an object of the stimulus-response data and based on the weight, the digital representation of the distribution type, and the digital representation of the range of inclination values.

Abstract: A control section performs control of displaying a plurality of different original images in a list form on a touch display section, clips a part of at least one of the plurality of different original images displayed in the list form in response to the detection of a second instruction operation by the user, acquires the clipped image, and performs control of displaying the clipped and acquired image in place of its original image displayed in the list form and subjected to the clipping, with the display size of the original image being maintained.

Abstract: A head-mounted display device with which a user can visually recognize a virtual image and an outside scene includes an outside-scene acquiring unit configured to acquire outside scene information including at least a feature of the outside scene in a visual field direction of the user, a position estimating unit configured to estimate, on the basis of at least two kinds of the outside scene information acquired by the outside-scene acquiring unit over time, a position of any target object present in a real world, and an augmented-reality processing unit configured to cause the image display unit to form, on the basis of the estimated position of the target object, the virtual image representing a virtual object to be added to the target object.

Abstract: Techniques are provided that include obtaining a vocabulary including a set of content indices that reference corresponding cells in a descriptor space based on an input set of descriptors. A plurality of local features of an image are identified based on the vocabulary, the local features being represented by a plurality of local descriptors. An associated visual word in the vocabulary is determined for each of the plurality of local descriptors. A plurality of global signatures for the image are generated based on the associated visual words, wherein some of the plurality of global signatures are generated using local descriptors corresponding to different cropped versions of the image, two or more of the different cropped versions of the image being centered at a same pixel location of the image, and an image recognition search is facilitated using the plurality of global signatures to search a document image dataset.

Abstract: In embodiments of animation using keyframing and projected dynamics simulation, an animation object is displayed with handles associated with object regions for the animation object, each handle being selectable for setting animation constraints on an object region. An animation simulator receives a user input designating a particular handle with an animation constraint, and sets the animation constraint on the particular handle for the associated object region. The animation simulator also receives another user input, designating a timing of the object region associated with the particular handle of the animation object through multiple frames in an animation sequence.

Abstract: The inner volume of an inhomogeneous three-dimensional object is visualized by a plurality of simulated visual rays. For a respective visual ray entering the object volume, i) a scatter position is determined along the visual ray, ii) a scatter direction is selected in dependence on a random process, and iii) the visual ray is scattered at the scatter position in the selected scatter direction. Steps i) to iii) are repeated until the visual ray is absorbed in the object volume or exits the object volume, wherein the exiting visual ray is incident on an illumination source and, in dependence on a brightness and/or color value of the illumination source, an illumination contribution of the visual ray to a respective visualization pixel is ascertained.

Abstract: A method of rendering an object including a path formed by a primitive includes: generating a tree corresponding to spaces partitioned by the primitive; selecting a pixel from the partitioned spaces; and acquiring a winding number of the selected pixel by detecting the tree.

Abstract: A system for providing a shared experience of virtual environments is disclosed. The system comprises a processing device for maintaining and rendering of a virtual environment to generate a plurality of visual components and a shared acoustic component representing the virtual environment, a plurality of interfaces connected to the processing device, each interface for connecting with a client device to continuously provide one of the plurality of visual components to the client device for display on the client device, and a sound device connected to the processing device for reproducing the shared acoustic component. The display of the plurality of visual components on respective client devices is synchronized with the reproduction of the shared acoustic component by the sound device. Furthermore, a method and a processing device for providing a shared experience of virtual environments and a corresponding client device are described.

Abstract: An image processing system is designed to generate a canvas view that has smooth transition between binocular views and monocular views. Initially, the image processing system receives top/bottom images and side images of a scene and calculates offsets to generate synthetic side images for left and right view of a user. To realize smooth transition between binocular views and monocular views, the image processing system first warps top/bottom images onto corresponding synthetic side images to generate warped top/bottom images, which realizes the smooth transition in terms of shape. The image processing system then morphs the warped top/bottom images onto the corresponding synthetic side images to generate blended images for left and right eye views with the blended images. The image processing system creates the canvas view which has smooth transition between binocular views and monocular views in terms of image shape and color based on the blended images.

Abstract: An augmented reality information displaying device according to the embodiment includes a storage, a display-position deciding unit, and a display controller. The storage stores augmented reality information associated with a real position. The display-position deciding unit decides a display position of the augmented reality information on a display screen of a transmission-type display device based on a real position of a user that visually recognizes the display screen, a real position of the display screen, the real position in the scene through the display screen associated with the augmented reality information. The display controller controls to display, at a display position decided by the display-position deciding unit, the augmented reality information corresponding to a mode according to positional relationship between the real position of the user and the real position associated with the augmented reality information in the scene.

Abstract: A non-limiting example game system includes a game apparatus, and a terminal device and a television are connected to the game apparatus. A game image that is displayed on the television is an image that various kinds of objects arranged in a virtual space are imaged by a virtual camera. The virtual camera follows a player object so as to keep a predetermined distance with the player object, and when the player object enters a grassland object with comparatively long length, for example, each grass object is deformed or moved so as to go away from the virtual camera. For example, a height of the grass object near the virtual camera is made comparatively low, and the height is gradually made high as it separates from the virtual camera.

Abstract: A display control method includes generating virtual space data representing a virtual space in which a virtual camera is arranged. The method further includes moving a visual field of the virtual camera along with movement of a head-mounted display (HMD). The method further includes generating visual-field image data based on the visual field of the virtual camera and the virtual space data. The method further includes displaying a visual-field image on the HMD based on the visual-field image data. The method further includes identifying a relative position relationship between the HDM and a user's hand. The method further includes determining whether or not a detected movement of the hand satisfies a first condition. The method further includes displaying a menu object in the visual field of the virtual camera based on the relative position relationship when the detected movement of the hand satisfies the first condition.

Abstract: The present disclosure relates to systems and methods that deliver 360° video streams, which may be used in virtual reality and augmented reality content. Namely, a 360° video stream may be divided into a plurality of video streams, each stream of which corresponds to a portion of a viewing volume or viewing sphere. Additionally, the original 360° video stream may be downsampled to a lower resolution 360° video stream. For a given user view angle, one or more of the plurality of video streams may be considered active streams and connected to a user interface or display for data download. In such a scenario, a user interface may be connected to at least one high resolution video stream that corresponds to the user view angle as well as a low resolution 360° video stream.

Abstract: In a method and system for the multisensory representation of an object, multidimensional digital model data of the object are provided to a processor. An actual three-dimensional object model is produced on the basis of at least part of the multidimensional digital model data of the object. The position of the object is recorded subsequently. At least part of the multidimensional digital model data of the object is displayed by an AR display device depending on the position of the object model.

Abstract: Systems and methods are described for automated generation of augmented reality (AR) content. An exemplary method includes receiving video data from an image sensor of an AR device, identifying a two-dimensional (2-D) geometric feature depicted in the received video data, and generating a virtual three-dimensional (3-D) geometric element by extrapolating the 2-D geometric feature into three dimensions. The method also includes modulating the generated virtual geometric element in synchrony with an audio input and displaying the modulated virtual geometric element on a video output of the AR device. The method may be executed in real-time.

Abstract: A system, method and software for producing a virtual scene to be viewed on an electronic display. A virtual reference plane is defined. The reference plane has peripheral boundaries. A virtual object is positioned above the reference plane in the virtual scene. Stereoscopic camera viewpoints are calculated that enable the virtual object to be imaged with the reference plane within the peripheral boundaries of the reference plane. The virtual object is digitally altered before and/or after being stereoscopically imaged. The altering includes bending, tapering or tilting a portion of the virtual object, and/or tilting a portion of the reference plane. A common set of boundaries are set for a superimposed image to create a final image.

Abstract: A method for patrol with scanning tags includes: installing electronic tags in various patrol locations, each of which includes an electronic paper displaying module and an identification mark mapping to one of the patrol locations to form mapping information; logging in a patrol server with a communication terminal; downloading a patrol route list which lists multiple patrol locations from the patrol server; scanning, with the communication terminal, the identification mark on the electronic tag when arriving at one of the patrol locations; and transmitting, with the communication terminal, a first data signal to the electronic tag to display a first patrol record based on the first data signal, and confirming the patrol position to be checked by transmitting the first patrol record to the patrol server.

Abstract: A communication device has a first data interface and a second data interface. A safe protection of the communication device against malicious code even under an easily breakable communication line between the communication device and a remote server is achieved by an intermediate protection unit located in a data communication line between the two data interfaces, wherein the intermediate protection unit blocks data in the direction from the second to the first data interface.

Abstract: An onboard device comprising a processor, a memory coupled to the processor, and an analog-to-digital (A/D) converter. The onboard device also comprises a transceiver and a global positioning system (GPS) receiver. In some embodiments, the memory of the onboard device stores a program that, when executed causes the processor to monitor voltage levels of a main battery of a vehicle for presence of a start sequence of a vehicle, detect movement of the vehicle, and send a message to an operations center indicating movement of the vehicle without occurrence of the start sequence.

Abstract: A motor vehicle driving style estimating system comprises: a measuring apparatus of a motion quantity of the motor vehicle; a processing apparatus connected to the measuring apparatus and configured to: define a value of a space corresponding to a measuring path; calculate, based on the motion quantity, an estimate of an energy consumed by the motor vehicle along the measuring path; calculate a reference energy associated to a reference behavior of the motor vehicle along the measuring path; and calculate an indication of the driving style dependent on: a difference between the consumed energy and reference energy, and on the space value.

Abstract: A identification information acquisition system provided in a working vehicle includes: a plurality of identification devices; and a plurality of communication devices that communicate with the plurality of identification devices. The plurality of communication devices include a first communication device and a second communication device, an operation of which is controlled by the first communication device. The first communication device is disposed at a first position and the second communication device is disposed at a second position in a working vehicle, a temperature at the first position being lower than a temperature at the second position.