Abstract: Ray tracing systems and computer-implemented methods are described for performing intersection testing on a bundle of rays with respect to a box. Silhouette edges of the box are identified from the perspective of the bundle of rays. For each of the identified silhouette edges, components of a vector providing a bound to the bundle of rays are obtained and it is determined whether the vector passes inside or outside of the silhouette edge. Results of determining, for each of the identified silhouette edges, whether the vector passes inside or outside of the silhouette edge, are used to determine an intersection testing result for the bundle of rays with respect to the box.

Abstract: A method and an intersection testing module for performing intersection testing of a ray with a convex polygon in a ray tracing system. The ray and the convex polygon are defined in a 3D space using a space-coordinate system. The ray is defined with a ray origin and a ray direction. A ray-coordinate system is used to perform intersection testing, wherein the ray-coordinate system has an origin at the ray origin, and wherein the ray-coordinate system has three basis vectors. A first of the basis vectors is aligned with the ray direction. A second and a third of the basis vectors: (i) are both orthogonal to the first basis vector, (ii) are not parallel with each other, and (iii) have a zero as one component when expressed in the space-coordinate system. A result of performing the intersection testing is outputted for use by the ray tracing system.

Abstract: A system, method or compute program product for generating stereoscopic images. One of the methods includes identifying, in a first three-dimensional coordinate system of a first three-dimensional virtual environment, a location and orientation of a first virtual object that is a virtual stereoscopic display object; identifying an eyepoint pair in the first virtual environment; identifying, in a second three-dimensional coordinate system of a second three-dimensional virtual environment, a location and orientation of a second virtual object that is in the second virtual environment; for each eyepoint of the eyepoint pair, rendering an inferior image of the second virtual object; for each eyepoint of the eyepoint pair, render a superior image of the first virtual environment, comprising rendering, in the superior image for each eyepoint, the corresponding inferior image onto the virtual stereoscopic display object; and display, on a physical stereoscopic display, the first virtual environment.

Abstract: A graphics processing system includes a tiling unit for performing tiling calculations and a hidden surface removal (HSR) unit for performing HSR on fragments of the primitives. Primitive depth information is calculated in the tiling unit and forwarded for use by the HSR unit in performing HSR on the fragments. This takes advantage of the tiling unit having access to the primitive data before the HSR unit performs the HSR on the primitives, to determine some depth information which can simplify the HSR performed by the HSR unit. Therefore, the final values of a depth buffer determined in the tiling unit can be used in the HSR unit to determine that a particular fragment will subsequently be hidden by a fragment of a primitive which is yet to be processed in the HSR unit, such that the particular fragment can be culled.

Abstract: Disclosed herein is a web-based videoconference system that allows for video avatars to navigate within a virtual environment. Various methods for efficient modeling, rendering, and shading are disclosed herein.

Abstract: Methods of determining the depth of a scene and associated systems are disclosed herein. In some embodiments, a method can include augmenting depth data of a scene captured with a depth sensor with depth data from one or more images of the scene. For example, the method can include capturing image data of the scene with a plurality of cameras. The method can further include generating a point cloud representative of the scene based on the depth data from the depth sensor and identifying a missing region of the point cloud, such as a region occluded from the view of the depth sensor. The method can then include generating depth data for the missing region based on the image data. Finally, the depth data for the missing region can be merged with the depth data from the depth sensor to generate a merged point cloud representative of the scene.

Abstract: Embodiments provide systems, methods, and computer storage media for fitting 3D primitives to a 3D point cloud. In an example embodiment, 3D primitives are fit to a 3D point cloud using a global primitive fitting network that evaluates the entire 3D point cloud and a local primitive fitting network that evaluates local patches of the 3D point cloud. The global primitive fitting network regresses a representation of larger (global) primitives that fit the global structure. To identify smaller 3D primitives for regions with fine detail, local patches are constructed by sampling from a pool of points likely to contain fine detail, and the local primitive fitting network regresses a representation of smaller (local) primitives that fit the local structure of each of the local patches. The global and local primitives are merged into a combined, multi-scale set of fitted primitives, and representative primitive parameters are computed for each fitted primitive.

Abstract: A method for creating a seamless scalable geological model may comprise identifying one or more geological scales, establishing a geological tied system, identifying one or more graphical resolution levels for each of the one or more geological scales, constructing the seamless scalable geological model, and producing a post-process model. A system for creating a seamless scalable geological model may comprise an information handling system, which may comprise a random access memory, a graphics module, a main memory, a secondary memory, and one or more processors configured to run a seamless scalable geological model software.

Abstract: A computer-implemented method and system for virtual visualization of overall regions are disclosed. Images of a overall region may be obtained by a server and used to generate a virtual model of the overall region. The server may generate a virtual environment that includes the virtual model of the overall region. A user may indicate a specific area of the virtual environment. The server may then dispatch an imaging vehicle to the location of the indicated area to capture additional image data representative of the indicated area. This additional set of image data may be used by the server to generate higher resolution virtual models of the indicated area that are integrated into the virtual environment.

Abstract: An ortho-image creation method includes: first photographing of photographing a road; second photographing of photographing an area covered by the obstacle from an altitude lower than the obstacle by a second photographing apparatus, and obtaining a plurality of second photographed images; first coordinate acquisition of acquiring three-dimensional coordinates; second coordinate acquisition of acquiring three-dimensional coordinates of a second feature point located in the area covered by the obstacle and included in at least two of the plurality of second photographed images; and ortho-image creation of creating a corrected ortho-image obtained by correcting at least a part of the area covered by the obstacle in the road surface to an area not covered by the obstacle, on the basis of the plurality of first photographed images, the plurality of second photographed images, the three-dimensional coordinates of the first feature point, and the three-dimensional coordinates of the second feature point.

Abstract: A plurality of images is obtained, whether as separate images or part of a video. The plurality of images is used to generate a three-dimensional (3D) model of the imagery. The 3D model is registered to a geographic coordinate system as a first registered 3D model. The first registered 3D model is merged with a second registered 3D model to generate a merged 3D model. A request including a value corresponding to a location within the geographic coordinate system that includes at least a portion of the merged 3D model is received from a client device. A message identifying at least a subset of points in the portion of the merged 3D model is sent to the client device, each point in the subset having a three-dimensional coordinate.

Abstract: Provided are a method and apparatus for acquiring virtual object data in augmented reality, the method including identifying at least one exposed component from three-dimensional image data corresponding to a target device, the exposed component being exposed to a view from outside of the target device, identifying a type of the target device from the three-dimensional image data corresponding to the target device, determining at least one main direction of the target device based on the type of the target device, and acquiring virtual object data for representing an appearance of the target device based on the at least one exposed component and at least one main direction.

Abstract: An interactive video game system includes at least one sensor and at least one display device disposed near a play area. The system also includes a controller communicatively coupled to the at least one sensor and the at least one display device, wherein the controller is configured to: receive, from the at least one sensor, the scanning data of the player in the play area; generate at least one model from the scanning data of the player; identify an action of the player in the play area based on the at least one model; generate the virtual representation for the player based on the at least one model and the action of the player; and present, on the display device, the virtual representation of the player in a virtual environment, wherein an action of the virtual representation is augmented relative to the action of the player.

Abstract: A method of augmenting reality of an image, comprising providing a lenticular lens for viewing an image, wherein the image is a lenticular image comprising at least two interlaced images. At least two fiducial markers are provided in the image. A first sensor located at a first distance from the image detects a first fiducial marker, and a second sensor located at a second distance from the image detects a second fiducial marker, wherein the detection of the each of the first and the second fiducial markers triggers a computing process delivering augmented reality to a user via a screen. The second distance is closer to the image than the first distance, and the second fiducial marker is capable of being detected by the second sensor from the second distance, but not from the first distance.

Abstract: Introduced here computer programs and associated computer-implemented techniques for establishing the dimensions of interior spaces. These computer programs are able to accomplish this by combining knowledge of these interior spaces with spatial information that is output by an augmented reality (AR) framework. Such an approach allows two-dimensional (2D) layouts to be seamlessly created through guided corner-to-corner measurement of interior spaces.

Abstract: The present disclosure relates to systems that capture a combination of image data and environmental data of the environment. The system uses the environmental data to create a detailed virtual scan of the environment. Computer generated models and images (“assets”) are inserted into the detailed virtual environment from the scan. These assets are scaled and placed within the virtual environment at specific locations and having a specific orientation. The scaled and positioned asset is then composited with the real-time video signal allowing a user to view the asset in real-time on a display.

Abstract: A correlation system can be implemented on a user device (e.g., smartphone) to perform image processing tasks e.g., point to point correlations for tasks such as alignment, tracking, and reconstruction of model data. The correlation system can implement normalized cross correlation in a least squares optimization scheme without use of approximations. Normalized cross correlation optimized via least squares can further implement global and local cost functions that are invariant to dynamic lighting conditions.

Abstract: Described herein are devices, systems, media, and methods using an augmented reality smartphone application to capture measurements of an interior or exterior space in real-time and generate a floorplan of the space and/or a 3D model of the space from the captured measurements in less than 5 minutes.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for changing perception of artificial reality content in a shared artificial reality environment. Various aspects may include determining user perception preferences associated with a user representation in the environment. Aspects may also include generating coordinates of a coordinate system and determining a distance between coordinates. Aspects may also include changing a perception parameter corresponding to the user representation based on the determined distances. Aspects may also include determining a visual style of the user representation based on an associated selected artificial reality application. Aspects may include providing instructions to display a virtual area including the user representation according to determined visual style and changed perception parameter.

Abstract: A measuring method includes the following. An image to be tested of an object to be tested with a first characteristic pattern is formed and is copied to form multiple images to be tested. The multiple images to be tested are superimposed to form a to-be-tested overlapped image which has the multiple first characteristic patterns. A reference image of a reference object with a second characteristic pattern is formed and is copied to form multiple reference images. The multiple reference images are superimposed to form a reference overlapped image which has the multiple second characteristic patterns. The to-be-tested overlapped image and the reference overlapped image are superimposed to generate a virtual moiré image having a moiré pattern different from the multiple first characteristic patterns and the multiple second characteristic patterns.

Abstract: Systems and techniques are provided for rendering virtual content in a scene. An example method includes determining a surface plane in a scene of a physical environment; rendering virtual content in a perspective at a location in the scene; rendering a content placement indicator associated with the virtual content on a first space of the surface plane, the content placement indicator indicating the first space for placement of the virtual content; determining one or more locations of one or more objects on a surface associated with the surface plane; and responsive to an input, rendering the content placement indicator on a second space of the surface plane, the second space being determined based on the one or more locations and input, the content placement indicator indicating the second space for placement of the virtual content.

Abstract: Systems and methods are provided for generating, selecting, modifying and/or otherwise configuring occluder(s) used in mixed-reality environments. Pose information of a trackable device worn or carried by a user is determined. Based on that pose information, an assumption regarding the user's own pose is determined. An occluder is then configured in a manner to correspond to the assumed pose of the user for use in the mixed-reality environment. By generating the occluder in this manner, improved battery life by the trackable device can be achieved relative to conventional systems that rely entirely on iterative scanning of the user's body to determine body position.

Abstract: The present disclosure generally relates to creating and editing avatars, and navigating avatar selection interfaces. In some examples, an avatar feature user interface includes a plurality of feature options that can be customized to create an avatar. In some examples, different types of avatars can be managed for use in different applications. In some examples, an interface is provided for navigating types of avatars for an application.

Abstract: An augmented reality system and an anchor display method thereof are provided. An environmental image is captured by an image capturing device disposed on a head-mounted device. A reference image block in the environmental image that matches a display image on a display is detected by performing feature matching between the environmental image and the display image. Position information of the reference image block in the environmental image is obtained. Depth information of the display is obtained according to an actual screen size of the display and a block size of the reference image block in the environmental image. At least one virtual object is displayed by the head-mounted device according to the position information and the depth information. The at least one virtual object is displayed as being anchored to at least one screen bezel of the display.

Abstract: An apparatus for estimating bio-information may include an optical sensor comprising a light emitter disposed on a substrate, and a plurality of light receiving groups which are arranged on a plurality of concentric circles on the substrate, at different distances from the light emitter, respectively, and a processor configured to drive one of the plurality of light receiving groups that is selected based on a type of the bio-information to be estimated, and estimate the bio-information of an object based on optical signals detected by the driven light receiving group.

Abstract: In general, techniques are described for a personal protective equipment (PPE) management system (PPEMS) that uses images of optical patterns embodied on articles of personal protective equipment (PPEs) to identify safety conditions that correspond to usage of the PPEs. In one example, an article of personal protective equipment (PPE) includes a first optical pattern embodied on a surface of the article of PPE; a second optical pattern embodied on the surface of the article of PPE, wherein a spatial relation between the first optical pattern and the second optical pattern is indicative of an operational status of the article of PPE.

Abstract: The present disclosure is directed to systems and methods for identifying regions of interest (ROIs) in images. A computing system may identify an image including an annotation defining an ROI. The image may have a plurality of pixels in a first color space. The computing system may convert the plurality of pixels from the first color space to a second color space to differentiate the annotation from the ROI. The computing system may select a first subset of pixels corresponding to the annotation based at least on a color value of the first subset of pixels in the second color space. The computing system may identify a second subset of pixels included in the ROI from the image using the first subset of pixels. The computing system may store an association between the second subset of pixels and the ROI defined by the annotation in the image.

Abstract: Disclosed is a system and method for segmentation of selected data. In various embodiments, automatic segmentation of fiber tracts in an image data may be performed. The automatic segmentation may allow for identification of specific fiber tracts in an image.

Abstract: An image processing apparatus is configured to perform processing of detecting an object by using a predetermined number of sample points referred to as particles, the processing including: executing a detection processing configured to calculate a weight for each of the particles, and detect the object by using the calculated weights; and executing a resampling processing configured to assign a particle number to each of the predetermined number of particles, calculate, for each particle, a comparative value by multiplying an average of the weights of the predetermined number of particles by the particle number, calculate, for each particle, a cumulative weight by adding the particle's own weight to the weights of all the particles assigned with the respective particle numbers smaller than the particle's own particle number, and perform a reselection process that executes reselection on the particles of all the particle numbers.

Abstract: A computing system configured to identify a region of interest in an image having a plurality of pixels, each of which corresponds to a feature score. The region of interest is a section of the image where feature points reside. The computing system is also configured to traverse one or more pixels in the region of interest in a spiral sequence starting from a center of the region of interest to edges of the region of interest to determine whether the corresponding pixel is a feature point.

Abstract: A method for detecting an object in a first distorted image using a sliding window algorithm, comprising: receiving an inverse of a mathematical representation of a distortion of the first distorted image; wherein the detection of an object comprises sliding a sliding window over the first distorted image, the sliding window comprising a feature detection pattern, and for each position of a plurality of positions in the first distorted image: transforming the sliding window based on the inverse of the mathematical representation of the distortion at the position, wherein the step of transforming the sliding window comprises transforming the feature detection pattern of the sliding window such that a resulting distortion of the feature detection pattern of the transformed sliding window corresponds to the distortion of the first distorted image at the position; and using the transformed sliding window comprising the transformed feature detection pattern in the sliding window algorithm.

Abstract: Example aspects of the present disclosure are directed to systems and methods for learning data augmentation strategies for improved object detection model performance. In particular, example aspects of the present disclosure are directed to iterative reinforcement learning approaches in which, at each of a plurality of iterations, a controller model selects a series of one or more augmentation operations to be applied to training images to generate augmented images. For example, the controller model can select the augmentation operations from a defined search space of available operations which can, for example, include operations that augment the training image without modification of the locations of a target object and corresponding bounding shape within the image and/or operations that do modify the locations of the target object and bounding shape within the training image.

Abstract: Automated systems and methods for training a multilayer neural network to classify cells and regions from a set of training images are presented. Automated systems and methods for using a trained multilayer neural network to classify cells within an unlabeled image are also presented.

Abstract: An automatic guided vehicle (AGV) comprising a mobile base including a drive train and configured to drive the AGV in a self-navigation mode within a facility, a first camera configured to capture first image data of objects within the facility, a second camera configured to capture second image data of objects within the facility, the second camera including a content filter, and a main control module configured to receive the first and second image data from the first and second cameras. The main control module executes a recognition neural network program. The neural network program recognizes targets in the first image data. The main control module also executes a supervisor program under user control. The supervisor program is receives the second image data and recognizes markers attached to targets in the second image data. The supervisor program produces a supervised outcome in which targets to which markers are attached are associated with categories based on user commands.

Abstract: A training method for a robust neural network based on feature matching is provided in this disclosure, which includes following steps. Step A, a first stage model is initialized. The first stage model includes a backbone network, a feature matching module and a fullple loss function. Step B, the first stage model is trained by using original training data to obtain a second stage model. Step C, the second stage model is attacked so as to generate PGD adversarial samples of the original training data, and the second stage model is trained again with the generated adversarial samples and the original training data. Step D, training parameters are adjusted and the second stage model is trained again, and parameters for which the model has highest accuracy on an original test set are saved.

Abstract: A computer implemented method of generating at least one shape of a region of interest in a digital image is provided.

Abstract: Systems and methods for facilitating communication with autonomous vehicles are provided. In one example embodiment, a computing system can obtain a first type of sensor data (e.g., camera image data) associated with a surrounding environment of an autonomous vehicle and/or a second type of sensor data (e.g., LIDAR data) associated with the surrounding environment of the autonomous vehicle. The computing system can generate overhead image data indicative of at least a portion of the surrounding environment of the autonomous vehicle based at least in part on the first and/or second types of sensor data. The computing system can determine one or more lane boundaries within the surrounding environment of the autonomous vehicle based at least in part on the overhead image data indicative of at least the portion of the surrounding environment of the autonomous vehicle and a machine-learned lane boundary detection model.

Abstract: Systems and methods for property feature detection and extraction using digital images. The image sources could include aerial imagery, satellite imagery, ground-based imagery, imagery taken from unmanned aerial vehicles (UAVs), mobile device imagery, etc. The detected geometric property features could include tree canopy, pools and other bodies of water, concrete flatwork, landscaping classifications (gravel, grass, concrete, asphalt, etc.), trampolines, property structural features (structures, buildings, pergolas, gazebos, terraces, retaining walls, and fences), and sports courts. The system can automatically extract these features from images and can then project them into world coordinates relative to a known surface in world coordinates (e.g., from a digital terrain model).

Abstract: Systems and methods are provided for determining a candidate identity of a person in video data based on a biometric motion signature corresponding to motion of a face of the person in the video data. Motion information is obtained corresponding to motion of the face in the video data. The motion information is provided as input to a neural network and the neural network generates the biometric motion signature in response. The biometric motion signature is compared with a plurality of biometric signatures stored in data storage. The candidate identity of the person is determined as a result of a correspondence between the biometric motion signature and a stored biometric signature of the plurality of biometric signatures.

Abstract: A style-based generative network architecture enables scale-specific control of synthesized output data, such as images. During training, the style-based generative neural network (generator neural network) includes a mapping network and a synthesis network. During prediction, the mapping network may be omitted, replicated, or evaluated several times. The synthesis network may be used to generate highly varied, high-quality output data with a wide variety of attributes. For example, when used to generate images of people's faces, the attributes that may vary are age, ethnicity, camera viewpoint, pose, face shape, eyeglasses, colors (eyes, hair, etc.), hair style, lighting, background, etc. Depending on the task, generated output data may include images, audio, video, three-dimensional (3D) objects, text, etc.

Abstract: Selections of content shared from a remote device during a video conference are copied to a destination of a computing device connected to the video conference live or at which a recording of the video conference is viewed. The content shared from the remote device during the video conference is output at a display of the computing device. A portion of the content is selected according to an instruction received from a user of the computing device while output at the display of the computing device to copy to a destination associated with software running at the computing device. The portion of the content is identified using a machine vision process performed against the content while output at the display of the computing device. The portion of the content is then copied to the destination.

Abstract: Methods of detecting and/or identifying an artificial target within an image are provided. These methods comprise: applying to a region of the image a primary classification algorithm for performing a feature extraction of the image region, the primary classification algorithm being based on a spectral profile defined by one or more spectral signatures with one or more features in at least part of the infrared spectrum; obtaining a relation between the extracted features of the image region and the spectral profile; verifying whether a level of confidence of the obtained relation between the extracted features and the spectral profile is higher than a first predetermined confirmation level; and, in case of positive (or true) result of said verification, determining that the image region corresponds to artificial target to be detected, thereby obtaining a confirmed artificial target. Systems and computer programs are also provided that are suitable for performing said methods.

Abstract: A computer-implemented method for allowing a user to visualize exposure data to facilitate catastrophe analysis includes receiving a wind speed probabilities data set; selecting a count of policies; generating an exposure map layer; and transmitting the map layer to a client device. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to: receive one or more map layers; display a set of filter criteria; receive an input of a user; and update the map graphical user interface.

Abstract: A feature extraction method of fruit spectrum includes taking a vector of each wavelength point in spectrum of samples as source data, and acquiring a sorting of all vectors by processing the source data by SPA; according to the sorting of the vectors, acquiring distribution points of each sample on a coordinate system; acquiring classification results of the samples by destructive analysis, and acquiring a number of first sample categories; acquiring a first Euclidean distance between the first sample categories; according to a sorting of the wavelength points, acquiring distribution points of each sample on the coordinate system; acquiring a number of second sample categories; acquiring a second Euclidean distance between the second sample categories; determining whether the first Euclidean distance is less than the second Euclidean distance; determine a (M+2)-th vector to be valid or invalid based on a comparison result.

Abstract: A method provides for assistance in recognition of an entity. A set of data and associated information corresponding to a plurality of entities known to an assisted user is received, such that an instance of the set of data and associated information includes identification of a respective entity of the plurality of entities known to an assisted user. Real-time data corresponding to a first entity is received from one or more devices capturing the real-time data. The real-time data is compared to the set of data and associated information corresponding to the plurality of entities known to the user to determine whether the first entity has a known relevance to the user, and in response to determining the first entity does have a known relevance to the user, the processor provides the identity and relevance of the first entity to the user.

Abstract: A device may detect, in a field of view of a camera, one or more components of an automated teller machine (ATM) device using a computer vision technique based on generating a three dimensional model of the one or more components. The device may identify the ATM device as a particular device or as a particular type of device based on the one or more components of the ATM device, or first information related to the ATM device. The device may identify a set of tasks to be performed with respect to the ATM device. The device may provide, for display via a display associated with the device, second information associated with the set of tasks as an augmented reality overlay. The device may perform an action related to the set of tasks, the ATM device, or the augmented reality overlay.

Abstract: Methods and apparatus for projecting augmented reality (AR) enhancements to real objects in response to user gestures detected in a real environment are disclosed. An example apparatus includes one or more processors to execute computer-readable instructions to identify a user gesture within a real environment based on data obtained from a motion sensor. The user gesture is associated with a target real object from among one or more real objects located within the real environment. The user gesture represents a desired shape of a desired virtual drawing to be projected to the target real object. The one or more processors are further to execute the instructions to determine an AR enhancement based on the user gesture and the target real object. The AR enhancement includes a virtual drawing having a shape corresponding to the desired shape of the desired virtual drawing.

Abstract: A system and method are provided for presenting self-diagnostic test instructions in the form of audiovisual messages. The system and method include collecting by a user of a testing device a biologic sample for use with a testing device, assigning correlative values as test results, and receiving the test results at a server disposed on a network. Some aspects of the system and method present test instructions to the user in the form of audiovisual messages. The audiovisual messages are provided to the user as a response to an interaction with a retail diagnostic product. In some aspects, the complete audiovisual message is presented before the user may complete a self-diagnostic test.

Abstract: Methods and apparatus to measure brand exposure in media streams are disclosed. Example apparatus disclosed herein are to determine a first histogram based on at least one of luminance components or chrominance components of a first frame of video, and determine a second histogram based on at least one of luminance components or chrominance components of a second frame of the video. Disclosed example apparatus are also to detect a transition in the video based on the first histogram and the second histogram, and responsive to the detection of the transition in the video. Disclosed example apparatus are further to process a region of interest within at least one of the first frame or the second frame to detect a logo in the region of interest.

Abstract: A computing system identifies broadcast video for a plurality of games in a first league. The broadcast video includes a plurality of video frames. The computing system generates tracking data for each game from the broadcast video of a corresponding game. The computing system enriches the tracking data. The enriching includes merging play-by-play data for the game with the tracking data of the corresponding game. The computing system generates padded tracking data based on the tracking data. The computing system projects player performance in a second league for each player based on the tracking data and the padded tracking data.