Abstract: A texture processing pipeline is configured to store decoded texture data within a cache unit in order to expedite the processing of texture requests. When a texture request is processed, the texture processing pipeline queries the cache unit to determine whether the requested data is resident in the cache. If the data is not resident in the cache unit, a cache miss occurs. The texture processing pipeline then reads encoded texture data from global memory, decodes that data, and writes different portions of the decoded memory into the cache unit at specific locations according to a caching map. If the data is, in fact, resident in the cache unit, a cache hit occurs, and the texture processing pipeline then reads decoded portions of the requested texture data from the cache unit and combines those portions according to the caching map.

Abstract: A method and system for performing general matrix-vector multiplication (GEMV) operations on a graphics processor unit (GPU) using Smart kernels. During operation, the system may generate a set of kernels that includes at least one of a variable-N GEMV kernel and a constant-N GEMV kernel. A constant-N GEMV kernel performs computations for matrix and vector combinations with a specific value of N (e.g., the number of columns in a matrix and the number of rows in a vector). Variable-N GEMV kernels may perform computations for all values of N. The system may also generate 1B1R kernels, constant-N variable-rows GEMV kernels, and variable-N variable-rows GEMV kernels. The system may generate constant-N variable-threads GEMV kernels, and variable-N variable-threads GEMV kernels. The system may also generate variable-threads-rows GEMV kernels for the set. This may include ConstN kernels (e.g., constant-N variable-threads-rows GEMV kernels), and VarN kernels (e.g., variable-N variable-threads-rows GEMV kernels).

Abstract: An image switching method and apparatus. The method includes: displaying an image in a first format; receiving an input instruction for switching the image from the first format to a second format; and displaying the image in the second format. The first format is a panorama image format or a wide-view image format, the second format is a panorama image format or a wide-view image format, and the first format is different from the second format. According to the method and the device in the embodiments of the present invention, a manner of simple and flexible interaction between a panorama image and a street side image is provided.

Abstract: An image generating apparatus includes an acquiring unit configured to acquire a captured image of a road, a region extraction unit configured to extract an image of a trapezoidal region is enclosed by two vanishing lines which are converged to a vanishing point in a depth direction of the captured image and two parallel lines which respectively intersect with the two vanishing lines from the captured image, a transformation unit configured to transform the image of the trapezoidal region into an image of a rectangular region using a geometric transformation model which transforms the trapezoidal region extracted by the region extraction unit into the rectangular region, and a generation unit configured to generate an image for enlarging and displaying a moving body or a structure on the road present at a distant view part of the captured image based on the transformed image having the rectangular region.

Abstract: An MRI system (100) acquires magnetic resonance data (158, 168) from a subject.

Abstract: The present disclosure relates to a display device, a display system and a resolution adjusting method. The display device comprises a display screen, and further comprises: a distance sensor and an adjusting unit, wherein the distance sensor comprises: a particle emitter for emitting a first particle beam to a viewer; a particle receiver for receiving the first particle beam reflected by the viewer, and wherein the adjusting unit adjusts a resolution of the display screen based on an energy density of the emitted first particle beam and an energy density of the received first particle beam.

Abstract: An image processing apparatus for encoding image data of a Bayer arrangement, comprising, a color separation unit configured to separate a plurality of color components of the image data into a plurality of plane image data based on the Bayer arrangement, a sum plane generation unit configured to generate plane image data of a sum plane by performing addition of components of the same color out of the plurality of plane image data, a difference plane generation unit configured to generate plane image data of a difference plane by performing subtraction of the components of the same color, and an encoding unit configured to compression-encode the plane image data, the encoding unit compression-encoding the plane image data of the sum plane and the difference plane for the plane image data of the components of the same color.

Abstract: An imaging apparatus includes an optical imaging system that converges light from an object; an imaging device that includes a plurality of pixels, receives the converged light, and converts the received light to an electric signal; a filter unit that is disposed between the optical imaging system and the imaging device and includes a plurality of color filters having different light transmission rate characteristics; and a transmission data compressing circuit that codes the electric signal. An overall light transmission rate characteristic of the filter unit differs randomly in different pixels of the imaging device, and the transmission data compressing circuit weights and codes the electric signal of each of the pixels by using a reciprocal of a proportion of the overall light transmission rate characteristic of the filter unit corresponding to each of the plurality of pixels of the imaging device relative to a wavelength characteristic common among the pixels.

Abstract: A computer-implemented method for recovering a digital image (x) from a sequence of observed digital images (y1, . . . , yT), includes: obtaining an observed digital image (yt); estimating a point spread function (ft) based on the observed image (yt); estimating the recovered digital image (x), based on the estimated point spread function (ft) and the observed image (yt); and repeating the above steps. In order to correct optical aberrations of a lens, a point spread function of the lens may be used.

Abstract: A method and apparatus for processing an array of pixels in a point cloud, comprises calculating local error limits for each distance value for each pixel in the processed point cloud data set. One may then determine the error bar. One begins a distance value adjusting loop by for each pixel in the processed point cloud data set by calculating the difference between the distance value in the pixel of the point cloud data set being processed and each of the neighboring pixels or the most suitable neighboring pixel distance value is determined whether or not the difference is within the range defined by the error bar. The number of neighboring pixels with their distance values within the error bar for the pixel being processed is counted.

Abstract: Imaging processing techniques using a trained convolution neural network (CNN) are described. In one or more implementations, an image processing system and method are provided for applying an image processing algorithm to a dataset of training images to generate a plurality of performance curves, constructing a loss function based upon the plurality of performance curves, training a convolutional neural network (CNN) to optimize the loss function to establish a trained convolutional neural network, predicting a specific tuning parameter for an image of interest using the trained convolution neural network and performing image processing of the image of interest using the specific tuning parameter and the image processing algorithm to generate a processed image of interest.

Abstract: Method, device, and program for solving the problem where a conventional image restoration method based on Bayesian probability theory uses nonlinear equations and requires a plurality of convolution operations, thereby not being appropriate for a single interaction multiple data-type (SIMD) super parallel computation processing device. This provides a method in which a computer causes a SIMD super parallel computation device to assign operations which include one convolution operation based on a Bayesian probability theory linear equation; a device based on the method; first and third programs for causing a computer to execute the program, and second and fourth programs for configuring the device to the computer and causing the device to run; and storage mediums for storing the programs. Optical degradation contained in TV video and images is reduced thereby restoring the TV video and images to a state close to the pre-degradation state of the TV video and images.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed towards automatic selection of regions for blur kernel estimation. In one embodiment, a process divides a blurred image into a regions. From these regions a first region and a second region can be selected based on a number of edge orientations within the selected regions. A first blur kernel can then be estimated based on the first region and a second blur kernel can be estimated for the second region. The first and second blur kernel can then be utilized to respectively deblur a first and second portion of the image to produce a deblurred image. Other embodiments may be described and/or claimed.

Abstract: Aspects saves modifications made to a depiction of a person within a photographic image uploaded to a networked service. In response to determining a presence of another depiction of the identified person in a different photographic image uploaded to the networked service, the modification saved to the profile data is automatically applied to another depiction of the identified person within the different photographic image to an initial publication of the uploaded, different photographic image on the networked service.

Abstract: A method and electronic device for processing an image in an electronic device. The method includes predicting the number of surfaces which can be partitioned in image data; determining an inverse distortion rendering method corresponding to the predicted number of surfaces as a method for inverse distortion rendering of the image data; rendering the image data to a distorted image based on the determined inverse distortion rendering method; and displaying the distorted image.

Abstract: An aspect of present principles is directed to methods, apparatus, systems and computer readable media for image processing. The image processing may include receiving a standard dynamic range (SDR) image or a receiver for receiving a standard dynamic range (SDR) image. It may further include determining an over-exposed region of the SDR image and determining a corrected luminance value for at least a pixel of the over-exposed region, or a processor configured to determine an over-exposed region of the SDR image and a corrected luminance value for at least a pixel of the over-exposed region. The corrected luminance value is determined based on at least one of a shape of the over-exposed region, luminance information of pixels surrounding the over-exposed region, and edge information of the pixels surrounding the over-exposed region. The over-exposed region may be an irregularly shaped region.

Abstract: A processor for signal reshaping receives an input image with an input bit depth. Block-based standard deviations are computed. The input codewords are divided into codeword bins and each bin is assigned a standard deviation value. For each bin, a standard deviation to bit-depth function is applied to the bin values to generate minimal bit depth values for each codeword bin. An output codeword mapping function is generated based on the input bit depth, a target bit depth, and the minimal bit depth values. The codeword mapping function is applied to the input image to generate an output image in the target bit depth.

Abstract: Systems, methods, and computer readable media to improve the operation of a display system are disclosed. Techniques disclosed herein selectively darken a region of an image so that when text or other information is rendered into that region, the contrast between the text or other information and the underlying image in that area is sufficient to ensure the text or other information is visible and readable. In one embodiment, a region into which information is to be rendered may be combined or blended with tone mapped values of those same pixels in accordance with a given function, where the function gives more weight to the tone mapped pixel values the closer those pixels are to the midline of the region and more weight to untone-mapped image pixel values the further those pixels are from the midline of the region.

Abstract: An imaging assembly includes a radiation camera configured to obtain position-sensitive radiation data of at least one source of interest. The assembly includes a controller includes a processor and tangible, non-transitory memory on which is recorded instructions for executing a method for reducing background interference in the position-sensitive radiation data in an image domain. The controller is programmed to generate a first set of image data (G1) from the position-sensitive radiation data with a first energy window. A second set of image data (G2) is generated from the position-sensitive radiation data with a second energy window such that the second energy window does not overlap with the first energy window. A third set of image data (G3) is generated having reduced background interference, based at least partially on the first and second sets of image data.

Abstract: Methods and systems of detecting tampering in a digital image includes using hybrid large feature mining to identify one or more regions of an image in which tampering has occurred. Detecting tampering in a digital image with hybrid large feature mining may include spatial derivative large feature mining and transform-domain large feature mining. In some embodiments, known ensemble learning techniques are employed to address high feature dimensionality. detecting inpainting forgery includes mining features of a digital image under scrutiny based on a spatial derivative, mining one or more features of the digital image in a transform-domain; and detecting inpainting forgery in the digital image under scrutiny at least in part by the features mined based on the spatial derivative and at least in part by the features mined in the transform-domain.

Abstract: A siding evaluation apparatus for use in identifying a characteristic of building siding is disclosed, together with methods and systems for identifying a characteristic of building siding using the siding evaluation apparatus. The siding evaluation apparatus includes a protrusion, clip, or other means for removably attaching to building siding by friction or pressure. The siding evaluation apparatus further includes a color chart holder adapted to hold a color chart for reference. The siding evaluation apparatus is attached to the siding and may be adjusted to display the color chart, which may be photographed together with a portion of the siding. Characteristics of the siding may then be determined based upon the captured photograph and a known reference area of the color chart.

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

Abstract: A method includes determining a permeability metric of vascular tissue of interest based on a first time enhancement curve and second time enhancement curve corresponding to a first contrast material and a second contrast material flowing through the vascular tissue of interest and generating a signal indicative thereof.

Abstract: A method of determining an indicator for the stability of a bone implant comprises providing a two- or three-dimensional image mage of a bone at a location where a bone implant is planned. Then determining a bone structural parameter, which is typically representative of trabecular bone texture at said location, from the two- or three-dimensional image, by a texture analysis of a two- or three-dimensional grey scale image in a region of interest at said location where the bone implant is planned. Finally, an indicator for the stability of the planned bone implant after implantation is determined from the bone structural parameter and from implant stability data.

Abstract: A system and methods for detecting particles and soluble chemical entities in body fluids consists of a system consisting of a microscopic apparatus, a sample chamber and reagents and methods used to detect, classify and enumerate particles and chemical entities in body fluids. Body fluids containing particles combined with reagents sediment to the bottom of a viewing chamber bringing them into the focal place of a digital microscopic detector. Particles identified as areas within a captured digital image that absorb or emit electromagnetic radiation can be further classified based on additional absorbed or emitted electromagnetic radiation within the predefined areas of the first digital image. Soluble chemical entities in body fluids are detected and concentrations determined using transmitted or emitted electromagnetic radiation using known chemical or antibody reactions, making the microscopic device a general purpose detector for in vitro determinations using body fluids.

Abstract: Methods for recognizing or identifying tooth types using digital 3D models of teeth. The methods include receiving a segmented digital 3D model of teeth and selecting a digital 3D model of a tooth from the segmented digital 3D model. An aggregation of the plurality of distinct features of the tooth is computed to generate a single feature describing the digital 3D model of the tooth. A type of the tooth is identified based upon the aggregation, which can include comparing the aggregation with features corresponding with known tooth types. The methods also include identifying a type of tooth, without segmenting it from an arch, based upon tooth widths and a location of the tooth within the arch.

Abstract: A workstation, a medical imaging apparatus including the same, and a control method for the same includes an input unit that receives information about a contour of an organ in a medical image obtained by imaging a subject and a control unit that corrects the contour of the organ in such a manner that the contour of the organ does not cross contours of one or more other organs located inside or outside the organ.

Abstract: Described are methods, systems, and apparatus, including computer program products for calibrating machine vision systems. A system includes: one or more cameras; a motion rendering device; and a calibration module. The calibration module is configured to acquire, from a first camera of the one or more cameras, a plurality of images of a calibration target comprising a calibration pattern that provides a plurality of calibration features; extract calibration features of the plurality of calibration features from the plurality of images, wherein physical positions of the plurality of calibration features are in a calibration target length unit associated with the calibration target; determine a ratio between the calibration target length unit and a motion rendering device length unit associated with the motion rendering device; and provide a first calibration for the first camera based on the ratio.

Abstract: There is provided a calibration apparatus for calculating a camera installation parameter with respect to a flat surface without preparing two sets of parallel lines on the flat surface, with respect to which the camera installation parameter is to be obtained. An acquirer acquires a photographed image of two linearly-extending lines substantially perpendicular to a flat surface. An extractor extracts the two linearly-extending lines from the acquired image through image processing. A calculator calculates a vanishing point from the extracted two linearly-extending lines and calculates a camera installation parameter with respect to the flat surface on the basis of coordinates of the vanishing point and given coordinates different from the coordinates of the vanishing point.

Abstract: This disclosure describes systems, methods, and apparatus for automating the verification of aerial vehicle sensors as part of a pre-flight, flight departure, in-transit flight, and/or delivery destination calibration verification process. At different stages, aerial vehicle sensors may obtain sensor measurements about objects within an environment, the obtained measurements may be processed to determine information about the object, as presented in the measurements, and the processed information may be compared with the actual information about the object to determine a variation or difference between the information. If the variation is within a tolerance range, the sensor may be auto adjusted and operation of the aerial vehicle may continue. If the variation exceeds a correction range, flight of the aerial vehicle may be aborted and the aerial vehicle routed for a full sensor calibration.

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

Abstract: Technologies for displaying graphical elements on a graphical user interface include a wearable computing device to generate a captured image. The wearable computing device analyzes the captured image to generate image location metric data for one or more prospective locations on the graphical user interface at which to place a graphical element. The image location metric data indicates one or more image characteristics of the corresponding prospective location. The wearable computing device determines appropriateness data for each prospective location based on the corresponding image location metric data. The appropriate data indicates a relative suitability of the corresponding location for display of the graphical element. The wearable computing device selects one of the prospective locations based on the appropriateness data and displays the graphical element on the graphical user interface at the selected prospective location.

Abstract: Sensor information acquisition section acquires surrounding information including three dimensional information of respective surrounding positions of subject vehicle, and positional information of subject vehicle. Road surface information extraction section generates road surface image in which acquired surrounding information is projected onto road surface on which subject vehicle is travelling. Environment image generation section generates environment image in which three dimensional information of respective surrounding positions included in surrounding information has been appended to positions corresponding to surrounding positions in generated road surface image. Based on acquired positional information of subject vehicle, stored image acquisition section acquires stored image corresponding to positional information of subject vehicle from database. Image matching section matches generated environment image against acquired stored image.

Abstract: An information processing apparatus includes an image acquisition unit configured to acquire an image obtained by imaging a target object onto which a pattern having a bright portion and a dark portion is projected by a projection unit, an allocation unit configured to allocate, to a pixel in the image, a label corresponding to luminance of the pixel by referring to a characteristic of the pattern, and a correspondence relationship derivation unit configured to derive a correspondence relationship between a position of the pattern in a projection plane of the projection unit and a position of the pattern in the acquired image and a three-dimensional coordinate derivation unit configured to derive three-dimensional coordinates of a surface of the target object based on the derived correspondence relationship.

Abstract: Apparatus and methods for detecting and utilizing saliency in digital images. In one implementation, salient objects may be detected based on analysis of pixel characteristics. Least frequently occurring pixel values may be deemed as salient. Pixel values in an image may be compared to a reference. Color distance may be determined based on a difference between reference color and pixel color. Individual image channels may be scaled when determining saliency in a multi-channel image. Areas of high saliency may be analyzed to determine object position, shape, and/or color. Multiple saliency maps may be additively or multiplicative combined in order to improve detection performance (e.g., reduce number of false positives). Methodologies described herein may enable robust tracking of objects utilizing fewer determination resources. Efficient implementation of the methods described below may allow them to be used for example on board a robot (or autonomous vehicle) or a mobile determining platform.

Abstract: Multi-scale deep reinforcement learning generates a multi-scale deep reinforcement model for multi-dimensional (e.g., 3D) segmentation of an object. In this context, segmentation is formulated as learning an image-driven policy for shape evolution that converges to the object boundary. The segmentation is treated as a reinforcement learning problem, and scale-space theory is used to enable robust and efficient multi-scale shape estimation. By learning an iterative strategy to find the segmentation, the learning challenges of end-to-end regression systems may be addressed.

Abstract: Techniques are disclosed for learning and modeling a background for a complex and/or dynamic scene over a period of observations without supervision. A background/foreground component of a computer vision engine may be configured to model a scene using an array of ART networks. The ART networks learn the regularity and periodicity of the scene by observing the scene over a period of time. Thus, the ART networks allow the computer vision engine to model complex and dynamic scene backgrounds in video.

Abstract: There is provided a method, a device and a system for modifying at least one parameter used by a video processing algorithm, such as a motion detection algorithm, an object detection algorithm, or an object tracking algorithm, for monitoring of a scene (102). The method comprises: receiving a first (105a) and a second (105b) video sequence of the scene (102), wherein the first video sequence (105a) is captured using a thermal camera (104a) such that the first video sequence (105a) comprises thermal information being indicative of temperatures in the scene (102), and applying the video processing algorithm to the second video sequence (105b), wherein at least one parameter used by the video processing algorithm is modified based on the thermal information comprised in the first video sequence (105a).

Abstract: In systems and methods disclosed herein, a transform may be determined for a given target object and background in an image between a native color space of the image and a second multi-dimensional color space representing a preferred color space for a tracker. The transform may then be applied to convert a plurality of pixels in the imaged scene to the second multi-dimensional color space thereby advantageously increasing a perceived contrast by the tracker between the target object and the background.

Abstract: A method and apparatus for analyzing a sequence of images. Signal-to-noise ratios are identified for potential tracks using a tree having hierarchies of nodes identifying potential positions for an object over a period of time and using the sequence of images. Each hierarchy in the hierarchies of nodes represents a time and the potential positions in the tree form the potential tracks for the object. A potential track is selected from the potential tracks as an established track for the object using the signal-to-noise ratios, and a detection of the object is reported.

Abstract: Systems and methods track one or more points between images. A point for tracking may be selected, at least in part, on a determination of how discriminable the point is relative to other points in a region containing the point. A point of an image being tracked may be located in another image by matching a patch containing the point with another patch of the other image. A search for a matching patch may be focused in a region that is determined based at least in part on an estimate of movement of the point between images. Points may be tracked across multiple images. If an ability to track one or more points is lost, information about the points being tracked may be used to relocate the points in another image.

Abstract: The wound assessing method and system of the present teachings provide a convenient, quantitative mechanism for diabetic foot ulcer assessment.

Abstract: Provided is a method and system for integrating multiple image markers to generate a single integral image marker for configuring content such as game content. The present invention proposes a method of expressing, in a global coordinate system, feature points for each image marker whose positions are expressed in their local coordinate system by calculating relative positions of the image markers and applying the calculated relative positions to the image makers other than a reference image maker to transform 3D positions of feature points in each image marker.

Abstract: A system, method, and computer program product for implementing a tree traversal operation for a tree data structure is disclosed. The method includes the steps of receiving at least a portion of a tree data structure that represents a tree having a plurality of nodes and processing, via a tree traversal operation algorithm executed by a processor, one or more nodes of the tree data structure by intersecting the one or more nodes of the tree data structure with a query data structure. A first node of the tree data structure is associated with a first local coordinate system and a second node of the tree data structure is associated with a second local coordinate system, the first node being an ancestor of the second node, and the first local coordinate system and the second local coordinate system are both specified relative to a global coordinate system.

Abstract: The invention discloses a method for synthesizing dynamic virtual figure, including: a synthesis server end receives a user request sent by a user and, according to information of the user request, obtains image files of all the components for synthesizing the required virtual figure; reading the corresponding image files of a component one by one according to layer numbers and transforming obtained component image files into a prescribed format; synthesizing the formatted component and previously synthesized middle figure; judging whether all components are synthesized, if all components are synthesized, writing the synthesized virtual figure into a virtual figure image file; otherwise, continuing to read corresponding image files of a component one by one according to layer numbers and transforming obtained component image files into the prescribed format. Adopting this method can implement the synthesis of dynamic virtual figures and thus provide better service for users.

Abstract: The implementations relate to a method and a device for interface display and an electronic device thereof. The method may include acquiring background information of an application page area adjoining to a system bar and configuring background of the system bar based on the background information. The background information may include related information reflecting a background color of the application page area. Therefore, users do not need to perform extra operations such as selecting colors. In addition to simplifying procedures and improving efficiency, the method may further avoid defragmented effects due to inconsistency between tones of the system bar and a control adjoining to the system bar. The method may provide a good visual effect for the users while presenting system information.

Abstract: A portable pervasive device includes a combined visual and thermal display. The user is able to detect texture of displayed objects visually and through touching the combined display. A software application pre-defines color codes and temperature settings for a plurality of textures on a graded scale including smooth, soft, and rough. The object is then shown on the display using the color codes and temperature settings for at lest one surface of the object.

Abstract: A computed tomography (CT) apparatus includes a data acquirer configured to acquire a first image corresponding to a first time point, a second image corresponding to a second time point, and a third image corresponding to a third time point based on a result of a CT scan on an object; an image reconstructor configured to acquire motion information of the object based on an amount of movement of the object between the first and second images and an amount of movement of the object between the first and third images, and obtain a target image by correcting at least one of the first, second and third images based on the motion information; and a display configured to display the target image.

Abstract: Method and system for obtaining tomosynthesis and material decomposition images of an object of interest using a system comprising an x-ray source facing a detector. The method comprises generating a 2D material decomposition image of an object of interest from at least two sets of acquisitions. Each set is performed at a different energy spectrum and comprises at least one projection image or a plurality of projection images acquired at different x-ray source angulation positions, and the 2D material decomposition image can be generated for a predetermined orientation selected from one of said different x-ray source angulation positions or from a virtual orientation. At least one of the plurality of 3D volume portion images and/or the 2D contrast enhanced material decomposition image are displayed for review by a health care professional.

Abstract: A tomography apparatus and a method of processing a tomography image are provided. The tomography apparatus includes a data acquirer configured to acquire a first image corresponding to a first time point and a second image corresponding to a second time point, based on data that is obtained from performing tomography on a moving object, acquire first information indicating a movement of the object between the first time point and the second time point, and determine a motion reliability indicating a degree to which the movement of the object corresponds to a physical movement, based on the first information. The tomography apparatus further includes an image reconstructor configured to reconstruct a target image indicating the object at a target time point, based on the motion reliability.