Abstract: An external environment recognition unit recognizes a construction section ahead of a host vehicle and recognizes that one or more recognition objects express entry possible/impossible information as to whether the host vehicle can enter the construction section. If the external environment recognition unit recognizes a traffic control person who directs traffic in the construction section as the recognition object and recognizes the entry possible/impossible information that is expressed by the traffic control person, an action plan unit (or an entry determination unit) decides whether to cause the host vehicle to enter the construction section or to stop before the construction section by using preferentially the entry possible/impossible information that is expressed by the traffic control person.

Abstract: A computed tomography (CT) system includes a rotatable gantry having an opening to receive an object to be scanned, an x-ray tube, a pixelated detector positioned on the rotatable gantry to receive the x-rays from the x-ray tube, and a computer programmed to acquire helical CT data, determine a sunrise (SR) view position for each pixel within a SR index image, and determine a sunset (SS) view position for each pixel within a SS index image, for a given reference image slice, wherein the SR view position is a first angle of an illumination range for a voxel and the SS view position is a last angle of the illumination range for the voxel, for all slices, rotate the SR index image and the SS index image through a projection index, and reconstruct an image based on the rotated SR index image and the SS index image.

Abstract: The disclosed embodiments relate to a material handling method that generates three-dimensional (3-D) point cloud data based on a field-of-view of an image capturing unit. A first set of cluster areas are extracted from a plurality of cluster areas based on orientation data of the 3-D point cloud data. Further, a two-dimensional depth map is generated based upon the 3-D point cloud data. A candidate region that corresponds to a cluster area from the first set of cluster areas is determined. A ratio of a cross-sectional area of the cluster area and a cross-sectional area of the container is determined that exceeds a first cross-sectional threshold. Accordingly, a classification score of the candidate region is determined when the determined ratio exceeds a first cross-sectional threshold. In response to classifying the candidate region as a region-of-interest, a navigation path in the container that prevents collision with the region-of-interest is defined.

Abstract: Provided is a video display system that includes a display device and an image processing device. The display device is mounted on the head of a user for use. The image processing device generates a plurality of unsynthesized images having different resolutions that are to be used for display by the display device, and transmits the generated unsynthesized images to the display device. The display device receives the unsynthesized images transmitted from the image processing device, and displays a display image that is obtained by synthesizing the unsynthesized images.

Abstract: A statistical method and device for customer flow volume. The method comprises: obtaining video image information in a preset monitoring area; performing video analysis on the video image information and determining a movement direction of a first target person appearing in the preset monitoring area according to an analysis result; obtaining, through statistics, incoming or outgoing customer flow volume of the actual detection area according to the determined movement direction of the first target person; reading a first terminal identifier, detected by a WiFi detector, of a WiFi terminal apparatus carried by the first target person; judging whether the first terminal identifier is present in a preset terminal identifier database for non-customer personnel; if so, decreasing the incoming or outgoing customer flow volume by 1; otherwise, making no change to the incoming or outgoing customer flow volume.

Abstract: The disclosure relates to a method for analysing cuttings exiting a borehole. The method comprises taking at least an image of a sample of cuttings on a background surface, obtaining spectra representative of the image in the (hue, saturation, brightness) coordinate space, wherein each spectrum is associated to a coordinate and is representative of the distribution of the values of the pixels for the coordinate. Based on the spectrum and the values of each pixel for the associated coordinate, classifying the pixel in one of a plurality of groups, wherein each group is representative of a type of objects within the image, i.e. cuttings and background surface. The method also comprises determining at least a cuttings zone in the image based on the classification of the pixels.

Abstract: A system and method of real-time surface reconstruction upon unstructured point clouds via a series of screen space operations are provided herein. A point occlusion operator, performed in a deferred pass upon a simple point splat, is used to determine point visibility and an ambient occlusion factor to estimate a solid angle of a visibility cone produced by each point in the splat by splitting the screen space local neighborhood of the point into sectors and accumulating the maximum viable sector angle. Points are valid or invalid. A density estimation pass is then used. Maps are used to determine the required number of region growing iterations to cover every invalid pixel. The density is then pruned by edge creep reduction to minimize the error around edges. A median filter is used to fill invalid pixels, while edge-preserving blur is applied to the valid pixels.

Abstract: A flatness detection method is provided for detecting component tilt regardless of measurement conditions. The flatness detection method is based on data of an electronic component captured by a 3D camera and is realized by acquiring position information and height information of a plurality of reference points of the electronic component, creating a virtual plane based on the position and the height information of at least three of the plurality of reference points, determining, based on the height information that takes, as a reference, the virtual plane of the reference points excluding selected points from the reference points, whether the virtual plane is a valid plane or an invalid plane, and detecting flatness of the component by taking the valid plane as a reference.

Abstract: A biosensor device (10) for in situ monitoring of deep-water sea-floor biological patterns (30), which biosensor platform (10) comprises a plurality of cameras (12) and a lightening system (14), wherein a plurality of coral nubbins (16) with a plurality of polyps (18) are prepared and fixed to a platform (11) of the biosensor platform (10) with a distance to each other such that there is no overlap on a picture frame (22) thereof, and wherein the cameras (12) and the lightening system (14) are arranged so as to take coral-silhouette-pictures (CSP:s) of the plurality of nubbins (16) in the picture frame (22). In this way, there is provided a biosensor device based on coral, or other deep-sea species, behavioural for surveillance and monitoring of a deep-water sea-floor.

Abstract: The invention provides systems, apparatus and methods for digital image processing system providing enhanced display of elements of images generated from x-ray and other forms of attenuation data converted to grayscale digital format. Such systems, apparatus and methods capture attenuation values used to render digital images and uses the data to identify distinct gradations of the grayscale, incorporating grayscale data, e.g., within and beyond the spectrum of human vision, then recursively delineates borders based on ranges of gradation, forming irregular multi-layer visual objects with delineated internal contouring and an outer boundary, and then enhancing each delineated layer and superimposes the enhancing display over the corresponding area of the original image, thereby revealing underlying morphology of masses previously obscured, hidden or “masked” from human vision. The invention operates on all digital images produced by attenuation values (i.e.

Abstract: A defect inspecting apparatus includes a reference image generator configured to generate a first reference image and a second reference image from design layout data. An image inspector is configured to obtain a first inspection image of a first inspection region of a photomask and a second inspection image of a second inspection region of the photomask. An operation processor is configured to extract a first coordinate offset by comparing the first inspection image with the first reference image and to extract a second coordinate offset by comparing the second inspection image with the second reference image.

Abstract: A method for identifying a boot stage of a BIOS of a computer device is provided. A control terminal receives screen information data indicative of a current BIOS screen image of the computer device, acquires current screen information based on the screen information data, acquires feature vector based on the current screen information, uses an image classification model to classify the current information into a screen category, and generates boot stage information indicative of a boot stage corresponding to the screen category.

Abstract: A non-invasive method to predict post-surgery vascular graft failure is provided. Computer Tomography Angiography (CTA) images are obtained of a patient post-surgery. A personalized three-dimensional computer model of the patient is derived from the obtained CTA images. The personalized three-dimensional computer model distinguishes a Computational Fluid Dynamics (CFD) model coupled with a closed-loop Lumped Parameter Network (LPN). Post-surgery vascular graft predictors are calculated from the personalized three-dimensional computer model indicative, i.e. predictors, of the post-surgery vascular graft failure or vascular stenosis.

Abstract: Systems and methods for generating authentic digital memorabilia are described. A signor may be provided a digital photograph. The signor's signature, written message, or voice message may be received. Biometric authentication or verification may be performed on the signor's handwriting or voice sample through comparison with stored samples. If the verification signifies a high likelihood signor's handwriting or voice sample is authentic, creation of digital memorabilia is performed by embedding signor's signature or written message in a digital photograph and linking the signor's voice message with the photograph. The digital memorabilia is accompanied by a certificate of authenticity and distributed to a customer or displayed on a website.

Abstract: A plurality of cameras obtain images in an environment. Calibration data about the translation and rotation of the cameras is used to support functionality such as determining a location of an object that appears in those images. To determine the calibration data, images are processed to determine features produced by points in the environment. A cluster is designated that includes the images of the same point as viewed from at least some of the cameras. A triangulation matrix and back-projection error are calculated for each cluster. These triangulation matrices and back-projection errors are then perturbed to find the translation and rotation that minimize eigenvalues and eigenvectors representative of the feature. The eigenvalues and eigenvectors are then used to determine the rotation and translation of the respective cameras with respect to an origin.

Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.

Abstract: Methods and systems for generating a size measurement of a body part of person for fitting a garment using a depth sensor.

Abstract: A method includes: receiving sensor data representing a subject within a field of vision associated with respective ones of a plurality of modular cameras associated with a composite camera and one or more geo-spatial characteristics associated with respective ones of the plurality of modular cameras; determining an arrangement of the composite camera based on the sensor data; generating digital content for respective ones of the plurality of modular cameras based on the sensor data; and generating combined digital content that represents a subject within a field of vision associated with the composite camera based on the digital content and the arrangement of the composite camera, wherein the field of vision associated with the composite camera includes at least some of fields of vision associated with the plurality of modular cameras.

Abstract: Described is a system for discriminant localization of objects. During operation, the system causes one or more processors to perform an operation of identifying an object in an image using a multi-layer network. Features of the object are derived from the activations of two or more layers of the multi-layer network. The image is then classified to contain one or more object classes, and the desired object class is localized. A device can then be controlled based on localization of the object in the image. For example, a robotic arm can be controlled to reach for the object.

Abstract: A method of plane tracking comprising: capturing by a camera a reference frame of a given plane from a first angle; capturing by the camera a destination frame of the given plane from a second angle different than the first angle; defining coordinates of matching points in the reference frame and the destination frame; calculating, using the first and second angles, first and second respective rotation transformations to a simulated plane parallel to the given plane; applying an affine transformation between the reference frame coordinate on the simulated plane and the destination frame coordinate on the simulated plane; and applying a projective transformation on the simulated plane destination frame coordinate to calculate the destination frame coordinate.