Abstract: Systems, methods, and apparatus embodiments for electric power grid and network registration and management of physical and financial settlement for participation of active grid elements in supply and/or curtailment of power, wherein Internet Protocol (IP)-based messages including IP packets are generated by transforming raw data content into settlement grade content. Settlement is provided for grid elements that participate in the electric power grid following initial registration of each grid element with the system, preferably through network-based communication between the grid elements and a coordinator, either in coordination with or outside of an IP-based communications network router. Messaging related to settlement is managed through a network by a Coordinator using IP messaging for communication with the grid elements, with the energy management system (EMS), and with the utilities, market participants, and/or grid operators.

Abstract: Embodiments and associated aspects of the disclosure permit regulation of dispense of a product in a self-serve environment via, at least in part, reconciliation of a product order originated in an access device, such as a point-of-sale (POS) device, and a product selection effected at a product dispenser configured to fulfill the product order.

Abstract: Disclosed subject matter includes systems and methods for providing a witnessed an electronically executed legal instrument, such as a limited power of attorney. The technology disclosed herein allows for the immediate transfer of a witnessed electronic document meeting today's current standards for witnessing of a document, including proximity of parties, and multiple forms of party identity authentication.

Abstract: A computer-implemented method includes detecting a first and second set of citations to a plurality of legal cases cited in a plurality of legal documents and a first legal document distinct from the plurality of legal documents, respectively. The computer-implemented method further includes determining a first and second set of tones corresponding to each citation in the first and second sets of citations, respectively. The computer-implemented method further includes determining a score for each tone in the first and second sets of tones, respectively. The computer-implemented method further includes detecting a first set of annotations corresponding to the first set of citations. The computer-implemented method further includes building a training model, based, at least in part, from at least a subset of the first set of annotations. The computer-implemented method further includes determining a second set of annotations corresponding to the second set of citations.

Abstract: Embodiments measure knowledge levels of students with respect to knowledge entities as they proceed through a course datagraph macrostructure, and dynamically adapt aspects of the macrostructure (and/or its embedded microstructures) to optimize knowledge acquisition of the students in accordance with their knowledge level. For example, a course consumption platform can parse the macrostructure and embedded microstructures to identify next microstructures to present to the student in such a way that dynamically adapts knowledge entities of the course to a student as a function of the student's present knowledge level associated with the student and difficulty levels of the presented microstructures.

Abstract: Methods and systems for providing location fencing within a controlled environment are disclosed herein. A location fencing server determines a location of a first inmate based on a first beacon device, and determines a location of a second inmate based on a second beacon device. Further, the location fencing server determines a proximity status based on the location of the first inmate and the location of the second inmate. Additionally, the location fencing server determines that the first inmate and the second inmate are in violation of a proximity policy based on the proximity status. In some embodiments, the location fencing server sends a notification to an employee device based on the violation of a proximity policy.

Abstract: Various systems and methods that may relate to referral and/or delivery services are described. Some embodiments may include billing merchants for delivery services in a consolidated fashion, some embodiments may include interactions with point of sale systems.

Abstract: A method and a system for controlling display parameters through multiple inter-integrated circuit (I2C) pipelines are provided. The method includes creating the multiple I2C pipelines to control the display parameters in one or more of the display devices. The method also includes sending control data to graphic cards associated with one or more display devices through the multiple I2C pipelines. Further, the method includes forwarding the control data from the graphic cards to the associated one or more display devices. Additionally, the method includes applying the display parameters automatically based on the control data.

Abstract: An information handling system includes a host processing system and a management controller. The host processing system includes a main processor that instantiates a management controller agent, a graphics processing unit (GPU), and a GPU throttle module. The management controller accesses the management controller via a first interface to obtain a performance status from the GPU, determine that the performance status is outside of a status threshold, and direct, via a second interface of the information handling system, the GPU throttle module to throttle the GPU to bring the performance status to within the status threshold.

Abstract: Methods, systems, and computer-readable media for capacity reservation for virtualized graphics processing are disclosed. A request is received to attach a virtual GPU to a virtual compute instance. The request comprises one or more constraints. Availability information is retrieved from a data store that indicates virtual GPUs available in a provider network and matching the one or more constraints. A virtual GPU is selected from among the available virtual GPUs in the availability information. The selected virtual GPU is reserved for attachment to the virtual compute instance. The virtual compute instance is implemented using CPU resources and memory resources of a physical compute instance, the virtual GPU is implemented using a physical GPU in the provider network, and the physical GPU is accessible to the physical compute instance over a network.

Abstract: One embodiment provides for a general-purpose graphics processing device comprising a general-purpose graphics processing compute block to process a workload including graphics or compute operations, a first cache memory, and a coherency module enable the first cache memory to coherently cache data for the workload, the data stored in memory within a virtual address space, wherein the virtual address space shared with a separate general-purpose processor including a second cache memory that is coherent with the first cache memory.

Abstract: A method and an apparatus that performs tile-based rendering. The method includes receiving a first drawcall used for rendering a first tile of a preceding frame; receiving a second drawcall used for rendering a second tile of a succeeding frame corresponding to a position of the first tile; generating a signature of the first drawcall and a signature of the second drawcall; comparing the signature of the first drawcall to the signature of the second drawcall. Based on a result of the comparison of the signature of the first drawcall and the signature of the second drawcall, rendering the second tile by using a result of rendering the first tile when a pre-set condition is satisfied.

Abstract: Systems, methods, and computer readable media to improve task switching operations in a graphics processing unit (GPU) are described. As disclosed herein, the clock rate (and voltages) of a GPU's operating environment may be altered so that a low priority task may be rapidly run to a task switch boundary (or completion) so that a higher priority task may begin execution. In some embodiments, only the GPU's operating clock (and voltage) is increased during the task switch operation. In other embodiments, the clock rate (voltages) of supporting components may also be increased. For example, the operating clock for the GPU's supporting memory, memory controller or memory fabric may also be increased. Once the lower priority task has been swapped out, one or more of the clocks (and voltages) increased during the switch operation could be subsequently decreased, though not necessarily to their pre-switch rates.

Abstract: Systems, apparatus, articles, and methods are described including operations to transpose image data between a linear-type storage format and a Y-tiled-type storage format.

Abstract: The present invention relates to a long-range discernible image generating apparatus and a method of operating the same, and particularly, to a long-range discernible image generating apparatus and a method of operating the same, which are capable of providing improved legibility. According to an embodiment of the present invention, a long-range discernible image generating apparatus is provided.

Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program reads a file representing a source image. The file specifies an interior image and a set of successive exterior images that correspond to a set of successive zoom levels. The interior image includes a plurality of pixels. Each pixel in the interior image has a particular size. Each exterior image in the set of successive exterior images includes a plurality of pixels configured to encompass the interior image. The plurality of pixels of each successive interior image have a successively larger size than the particular size. The program generates the source image based on the interior image and the set of successive exterior images. The program receives a selection of a zoom level in the set of successive zoom levels. The program generates a target image based on the selected zoom level and the source image.

Abstract: Methods, systems, and apparatus, including an apparatus for determining pixel coordinates for image transformation and memory addresses for storing the transformed image data. In some implementations, a system includes a processing unit configured to perform machine learning computations for images using a machine learning model and pixel values for the images, a storage medium configured to store the pixel values for the images, and a memory address computation unit that includes one or more hardware processors. The processor(s) are configured to receive image data for an image and determine that the dimensions of the image do not match the dimensions of the machine learning model. In response, the processor(s) determine pixel coordinates for a transformed version of the input image and, for each of the pixel coordinates, memory address(es), in the storage medium, for storing pixel value(s) that will be used to generate an input to the machine learning model.

Abstract: A system and method for providing high resolution image through super-resolution reconstruction. The system comprises a frame buffer, a convolutional neural network module, an image processing module, and a bi-directional prediction module. After the frame buffer has received high-resolution image with low frames per second and low-resolution image with high frames per second, both are captured by an image capturing module, image processing with super-resolution reconstruction can be performed through the cooperation of the convolutional neural network module, the image processing module and the bi-directional prediction module. In other words, a frame with super-resolution can be calculated through a well-trained convolutional neural network.

Abstract: A first image and a second image with resolutions different from each other are generated from an image captured by an imaging unit, and the first image and the second image are subject to different types of image processing. A virtual image is generated by calculating a position and an orientation of the imaging unit based on the processed first image. A composite image is generated by combining the generated virtual image with the second image subjected to the image processing, and the generated composite image is used as a display image.

Abstract: A head-mounted display (HMD) divides an image into a high resolution (HR) inset portion at a first resolution, a peripheral portion, and a transitional portion. The peripheral portion is downsampled to a second resolution that is less than the first resolution. The transitional portion is blended such that there is a smooth change in resolution that corresponds to a change in resolution between a fovea region and a non-fovea region of a retina. An inset region is generated using the HR inset portion and the blended transitional portion, and a background region is generated using the downsampled peripheral portion. The inset region is provided to a HR inset display, and the background region is provided to a peripheral display. An optics block combines the displayed inset region with the displayed background region to generate composite content.

Abstract: It is configured such that decoded images with favorable image quality are obtained, even in the case of using extended macroblock sizes. A deblocking filter 24 applies filtering to reduce blocking artifacts from an encoded stream in which image data has been encoded in individual blocks. A filter strength adjuster 41 adjusts the filter strength according to block sizes of the predictive image data. For example, during image encoding, the filter strength is adjusted according to the block size of the predictive image data yielding the best encoding efficiency generated using filtered and decoded image data. It may also be configured such that filtering is applied to remove blocking artifacts from decoded image data during image decoding, with the filter strength being adjusted according to the block sizes of the predictive image data.

Abstract: The present disclosure discloses a method for reducing ringing artifacts in an X-ray image, comprising: acquiring an X-ray image by scanning an object, wherein the X-ray image comprises grid line artifacts; applying a first bandwidth filter and a second bandwidth filter respectively to the X-ray image so as to obtain a filtered first image and a filtered second image, wherein the first bandwidth filter and the second bandwidth have different bandwidths; constructing a weighting map according to the X-ray image; and fusing the filtered first image and the filtered second image with the weighting map so as to obtain an output image. The present disclosure also discloses a system using the above method.

Abstract: The disclosure relates generally to techniques for using information about a user's actual or predicted pupil location for correcting optical distortions that are specific to an optical lens and display assembly through which the user is viewing one or more images. The described techniques may include identifying and mapping optical distortions specific to an optical lens and display assembly, and using such mapped optical distortions to correct images displayed to a wearer or other user receiving images via the assembly, such as based at least in part on pupil location of the wearer or other user. As one example, the one or more optical lens may be mounted inside a head-mounted display (HMD) that also includes a display panel or other image source for an eye of a wearer, and if so one or more pupil tracking mechanisms may be integrated into the HMD.

Abstract: A method includes shooting an nth frame of image at a first angle, where a projection of a distance value of a first pixel point of the nth frame of image to an optical center onto an optical axis direction is a first distance value, and a projection of a distance value of an ith pixel point of the nth frame of image to the optical center onto the optical axis direction is a second distance value, obtaining a third and a fourth distance value, obtaining a correction coefficient of the ith pixel point of the nth frame of image according to the first, the second, the third, and the fourth distance value, and correcting a location of the ith pixel point of the nth frame of image according to the correction coefficient using a location of an ith pixel point of the first frame of image as a reference.

Abstract: An image processing method determines a geometric transform of a suspect image by efficiently evaluating a large number of geometric transform candidates in environments with limited processing resources. Processing resources are conserved by using configurations of dot product operations to produce both least squares mappings for each candidate and an error metric. Geometric transform candidates are rapidly winnowed to a smaller number of promising candidates based on the error metric and the promising candidates are refined further in subsequent iterations. An optimized method for determining updated coordinates for potential reference signal components in the suspect image evaluates a suspect image block at plural neighborhoods and builds a look up table that provides updated coordinates for each of the neighborhoods.

Abstract: A system and method for lossy image and video compression and transmission that utilizes a neural network as a function to map a known noise image to a desired or target image, allowing the transfer only of hyperparameters of the function instead of a compressed version of the image itself. This allows the recreation of a high-quality approximation of the desired image by any system receiving the hyperparameters, provided that the receiving system possesses the same noise image and a similar neural network. The amount of data required to transfer an image of a given quality is dramatically reduced versus existing image compression technology. Being that video is simply a series of images, the application of this image compression system and method allows the transfer of video content at rates greater than existing technologies in relation to the same image quality.

Abstract: A method for detecting a crack in a structural component includes receiving, with a processor, signals indicative of at least one image for a critical location in the structural component; determining, with the processor, at least one shape in the at least one image, the at least one shape being representative of a structure of the critical location; representing, with the processor, at least one region around the structure into a matrix; and applying, with the processor, image processing on the matrix to detect cracks in the at least one region of the structural component.

Abstract: A three-dimensional image processing apparatus includes: an image capturing part for acquiring reflected light to capture a plurality of pattern projected images; a distance image generating part capable of generating a distance image based on the plurality of pattern projected images; a tone conversion part for tone-converting the distance image generated in the distance image generating part to a low-tone distance image that has a lower number of tones than the number of tones of the distance image and is obtained by replacing height information in the distance image with a shade value of the image; and a tone conversion condition automatic setting part for automatically setting, based on the height information in the distance image, a tone conversion parameter for prescribing a tone conversion condition at the time of tone-converting the distance image to the low-tone distance image in the tone conversion part.

Abstract: A method for monitoring live poultry intended for slaughter includes checking managing parameters and process parameters of poultry flocks from breeding farms, and monitoring transportation of the flocks to a slaughterhouse and handling thereof at the slaughterhouse. Gas stunning parameters of the poultry are checked prior to throat-cutting thereof. Video shooting of the poultry's reactions during the stunning step is done to visually verify a degree of well-being thereof. Computer records are made available wherein a single video file corresponds to each poultry flock or group of flocks in which images of the visible reactions of the poultry are combined and synchronized with said managing and process parameters.

Abstract: A system includes a welding device, one or more cameras, and a controller coupled to the one or more cameras. The welding device includes a first set of visual markers oriented in a first direction and a second set of visual markers oriented in a second direction. Each set of visual markers includes at least three visual markers. The one or more cameras are configured to observe the first set of visual markers when the first direction is directed toward the one or more cameras, and to observe the second set of visual markers when the second direction is directed toward the one or more cameras. The controller is configured to track a position and an orientation of the welding device based at least in part on detection of a threshold quantity of the first set of visual markers or the threshold quantity of the second set of visual markers.

Abstract: A feature portion desired by a user out of an inspection target image is accurately positioned. A standard region is set so as to surround a standard pattern in a standard image of a product to be a standard for an inspection target. A sorting region, which is a region for sorting a plurality of candidates similar to the standard pattern, is set in the inspection image. The standard pattern is searched from the inspection image, to extract a plurality of candidates similar to the standard pattern. The sorting region is disposed with respect to each of the plurality of candidates for the standard pattern, extracted in the extraction step, to sort a candidate for the standard pattern based on an evaluation value of the sorting region disposed with respect to each of the plurality of candidates for the standard pattern.

Abstract: A system for processing an image includes a three-dimensional camera that captures an image of a dairy livestock, wherein the image comprises a plurality of adjacent pixels, each pixel associated with a depth location. The system further includes a processor communicatively coupled to the three-dimensional camera. The processor determines that the depth locations of a first portion of the adjacent pixels fluctuate beyond a predetermined threshold over time, and discards the first portion of the adjacent pixels from the image based at least in part upon the determination.

Abstract: A method for checking a faultless joint between a first and a second component of a medical device, namely a drip chamber and a spike, wherein the first component has an annular coupling edge facing downwardly to be sprayed interiorly with a liquid solvent. The solvent is mixed with a tracer detectable through ultraviolet or infrared light and the coupling edge is illuminated with a ultraviolet or infrared light so as to make an image of the sprayed solvent, which is reflected and captured by an electronic scanning device configured to establish whether such image is faultless, visible through a tracer.

Abstract: The invention provides a sliced image processing method including following steps: analyzing a sliced object in a sliced image to determine whether the sliced object has a first contour line segment and a nearest second contour line segment, where the second contour line segment is located within a region encircled by the first contour line segment; determining whether vector directions of the first contour line segment and the second contour line segment are opposite when the sliced object has the first contour line segment and the second contour line segment, and correcting the vector direction of at least one of the first contour line segment and the second contour line segment when the vector directions of the first contour line segment and the second contour line segment are not opposite.

Abstract: A method comprises the step of determining a minimum length of a lesion based on an imaging modality used to capture an image of the lesion and a slice thickness of the image, generating an extent cursor corresponding to the minimum size of the lesion, the extent cursor having a circular shape with a diameter corresponding to the minimum length and displaying the image of the lesion with the extent cursor positioned thereover.

Abstract: Method for analyzing data provided by Magnetic Resonance Imaging with dynamic administration of contrast medium in patients with locally advanced rectal cancer, after neoadjuvant radio-chemotherapy, comprising: making available pre- and post-treatment digital images, having one or more regions of interest identified; splitting the regions of interest into portions; calculating first and second time-intensity curves for each portion of the regions of pre- and post-treatment interest, respectively; calculating the maximum signal difference and gradient of the wash-out section for the curves calculated; calculating the median value of the maximum signal difference and of the gradient calculated; calculating the percentage variation between the median values of the maximum signal difference and of the gradient of the wash-out section calculated for each of the first and second curves; linearly combining percentage variations of the maximum signal difference and of the gradient of the wash-out section, to define a

Abstract: Inspection of a shape-fixed medicine is performed before packing. A medicine inspection assistance device includes: a medicine support part for rotatably supporting a shape-fixed medicine by a first rotating roller and a second rotating roller, and a medicine imaging part having an imaging means for imaging the shape-fixed medicine supported by the medicine support part from above. The medicine support part is configured such that a contact position between the first rotating roller and the shape-fixed medicine is located above the second rotating roller and the contact position is closer to an axis of the first rotating roller than a gravity center position of the shape-fixed medicine.

Abstract: A method for computer-aided diagnosis of skin lesions includes obtaining a dermoscopic image, convolving the dermoscopic image in a plurality of convolutional layers, obtaining deconvolved outputs of at least two convolutional layers of the plurality of convolutional layers, obtaining side-output feature maps by applying loss functions to the deconvolved outputs of the at least two convolutional layers, obtaining a first concatenated feature map by concatenating the side-output feature maps with different first weights, obtaining a second concatenated feature map by concatenating the side-output feature maps with different second weights, and producing a final score map by convolving the first and second concatenated feature maps in a final convolutional layer followed by a loss layer. Also disclosed: a computer-readable medium embodying instructions for the method, and an apparatus configured to implement the method.

Abstract: A method and system for automated spatially-consistent multi-scale detection of anatomical landmarks in medical images is disclosed. A discrete scale-space representation of a medical image of a patient is generated. A plurality of anatomical landmarks are detected at a coarsest scale-level of the discrete scale-space representation of the medical image using a respective trained search model trained at the coarsest scale-level for each of the plurality of anatomical landmarks. Spatial coherence of the detected anatomical landmarks is enforced by fitting a learned robust shape model of the plurality of anatomical landmarks to the detected anatomical landmarks at the coarsest scale-level to robustly determine a set of the anatomical landmarks within a field-of-view of the medical image.

Abstract: An example method for diagnosing tumors in a subject by performing a quantitative analysis of a radiological image can include identifying a region of interest (ROI) in the radiological image, segmenting the ROI from the radiological image, identifying a tumor object in the segmented ROI and segmenting the tumor object from the segmented ROI. The method can also include extracting a plurality of quantitative features describing the segmented tumor object, and classifying the tumor object based on the extracted quantitative features. The quantitative features can include one or more texture-based features.

Abstract: A system for computer-aided triage can include a router, a remote computing system, and a client application. A method for computer-aided triage can include determining a parameter associated with a data packet, determining a treatment option based on the parameter, and transmitting information to a device associated with a second point of care.

Abstract: A method and an apparatus for background subtraction highly applicable in autonomous driving scenarios are described. The method involves a reduction of illumination effects by constructing a normality background image from a normality model based on a plurality of baseline images taken under different illuminating conditions. A subtracted image is obtained by subtracting the normality background image from a scene image pixel-wise (i.e., pixel-by-pixel). The scene image may contain one or more foreground objects. The foreground objects are identified by highlighting the pixels in the subtracted image whose intensity is more than a predetermined standard deviation in the normality model. An illumination-invariant color space transformation algorithm may optionally be utilized to further reduce the variant illumination effects.

Abstract: A method for an attention-driven image segmentation by using at least one adaptive loss weight map is provided to be used for updating HD maps required to satisfy level 4 of autonomous vehicles. By this method, vague objects such as lanes and road markers at distance may be detected more accurately. Also, this method can be usefully performed in military, where identification of friend or foe is important, by distinguishing aircraft marks or military uniforms at distance. The method includes steps of: a learning device instructing a softmax layer to generate softmax scores; instructing a loss weight layer to generate loss weight values by applying loss weight operations to predicted error values generated therefrom; and instructing a softmax loss layer to generate adjusted softmax loss values by referring to initial softmax loss values, generated by referring to the softmax scores and their corresponding GTs, and the loss weight values.

Abstract: Methods and systems are disclosed for segmenting an image. First and second frames of image data are generated at different times. A first portion of the first frame is compared to image data of the second frame, and a second portion of the second frame is selected based on the comparison. A displacement vector between the first portion and the second portion is calculated, where the displacement vector represents relative movement over time between the image data represented by the first portion and the image data represented by the second portion. An image is output with an indicator, and the location of the indicator on the image is determined by using the calculated displacement vector. The indicator can serve to distinguish between items in an imaging view.

Abstract: Approaches presented herein enable tracking a physical object with a holographic projection, and, more specifically, enhancing a view of an object by tracking the object with a 3-D holographic projection. A holographic object tracking projection system receives, from a sensor, a feed of an area containing a physical object and locates a position of the physical object in the area based on the feed. The system creates a visible holographic object to mark the physical object, and projects the holographic object, using a holographic projector, at the position of the physical object. The holographic object can be a shape that surrounds the physical object in order to increase a visibility of the physical object. The physical object may move, and, as the physical object moves, the holographic object tracking projection system tracks this movement and adjusts the holographic object to match the movement of the physical object.

Abstract: Method and system for tracking moving objects in a video with non-stationary background is provided. The method comprises estimation of non-stationary background and determining an approximate foreground for each image that learns the background model over time by incorporating various constraints on image pixels. Then, weights based upon spatio-temporal statistical properties of the extracted foreground blobs and blob edge overlap are used to identify and track with bounding boxes displayed for one or more true objects.

Abstract: The present invention provides a sun position tracking method based on a black sun effect of an image sensor, a computer program including commands for causing a computer system to perform the method, and a solar sensor using the method. The sun position tracking method includes processing a plurality of images captured using a plurality of image sensors installed to capture a plurality of images of the sun irrespective of the position of the sun to estimate the center point of the black sun and track the position of the sun.

Abstract: An autonomous store system that analyzes camera images to track people and their interactions with items using a processor that obtains a 3D model of a store that contains items and item storage areas. Receives images from cameras captured over a time period and analyzes the images and the 3D model of the store to detect a person in the store based on the images, calculates a trajectory of the person, identifies an item storage area proximal to the trajectory of the person during an interaction time period, analyzes two or more images to identify an item within the item storage area that is moved during the interaction time period. The images are captured within or proximal in time to the interaction time period, and the images contain views of the item storage area, and attribute motion of the item to the person. Enables calibration and placement algorithms for cameras.

Abstract: A method for merging object detection information detected by object detectors, each of which corresponds to each of cameras located nearby, by using V2X-based auto labeling and evaluation, wherein the object detectors detect objects in each of images generated from each of the cameras by image analysis based on deep learning is provided. The method includes steps of: if first to n-th object detection information are respectively acquired from a first to an n-th object detectors in a descending order of degrees of detection reliabilities, a merging device generating (k-1)-th object merging information by merging (k-2)-th objects and k-th objects through matching operations, and re-projecting the (k-1)-th object merging information onto an image, by increasing k from 3 to n. The method can be used for a collaborative driving or an HD map update through V2X-enabled applications, sensor fusion via multiple vehicles, and the like.

Abstract: A measurement apparatus that is capable of positively generating a projection pattern suitable for a to-be-read object. A camera scanner as the measurement apparatus projects a projection pattern formed by a plurality of projection lines on a to-be-read object to thereby measure the bending of the to-be-read object. A distance to the to-be-read object is measured, and distance distribution information of the to-be-read object for identifying a shape, a size, and a position of the to-be-read object is generated based on the measured distance. The projection pattern is generated based on the generated distance distribution information of the to-be-read object.