Abstract: An medical image processing method comprises generating a first segmented medical image in accordance with a first segmentation model and based on an original medical image that comprises a plurality of pixels. The method also comprises determining a foreground point and a background point according to the initial target region of the first segmented image. The method further comprises: for each pixel of the plurality of pixels of the original image, determining a first image distance between the respective pixel and the foreground point and a second image distance between the respective pixel and the background point. The method further comprises obtaining a foreground point range image and a background point range image corresponding to the original image, and generating a second segmented image in accordance with a second segmentation model based on the original image, the foreground point range image, and the background point range image.

Abstract: Systems and methods for image-based biological sample constituent analysis are disclosed. For example, image data corresponding to an image having a target constituent and other constituents may be generated and utilized for analysis. The systems and processes described herein may be utilized to differentiate between portions of image data corresponding to the target constituent and other portions that do not correspond to the target constituent. Analysis of the target constituent instances may be performed to provide analytical results.

Abstract: Methods and systems for characterizing tissue of a subject are disclosed. The method includes retrieving a time series of angiography images of tissue of a subject, defining a plurality of calculation regions, generating a time-intensity curve for each respective calculation region, calculating a rank value for each respective calculation region based on one or more parameters derived from the time-intensity curve; and generating a viewable image in which on the image position of each calculation region an indication is provided of the calculated rank value for that calculation region. Also disclosed are methods and systems for generating first and second time-intensity curves for respective first and second calculation regions, calculating first and second rank values for the respective calculation regions based on first and second pluralities of parameters selected to approximate the respective time-intensity curves, and generating a spatial map of the first and second calculated rank values.

Abstract: Methods and systems for image processing are provided. Image data may be obtained. The image data may include a plurality of voxels corresponding to a first plurality of ribs of an object. A first plurality of seed points may be identified for the first plurality of ribs. The first plurality of identified seed points may be labelled to obtain labelled seed points. A connected domain of a target rib of the first plurality of ribs may be determined based on at least one rib segmentation algorithm. A labelled target rib may be obtained by labelling, based on a hit-or-miss operation, the connected domain of the target rib, wherein the hit-or-miss operation may be performed using the labelled seed points to hit the connected domain of the target rib.

Abstract: Described herein is a novel method and system for segmentation of the spine using 3D volumetric data. In embodiments, a method includes an extracting step, localization step, and segmentation step. The extracting step comprises detecting the spine centerline and the spine canal centerline. The localization step comprises localizing the vertebra and intervertebral disc centers. Background and foreground constraints are created for each vertebra digit. Segmentation is performed for each vertebra digit and based on the hard constraints.

Abstract: A method for segmenting an image includes receiving one or more object seeds associated with one or more first object portions represented by a first image and receiving one or more background seeds associated with one or more first background portions represented by the first image. A second image representing one or more second object portions and one or more second background portions is received, wherein the first image comprises a plurality of subportions and the second image is a subportion of the plurality of subportions of the first image. The second image is processed based on the one or more object seeds and the one or more background seeds to determine the one or more second object portions and the one or more second background portions.

Abstract: A method and system for locating a target object in a target scene. The method may include obtaining a depth image of the target scene. The depth image may include a plurality of pixels. The method may also include, for each of the plurality of pixels of the depth image, determining a first target coordinate under a target coordinate system. The method may further include generating a marking image according to the depth image and the first target coordinates of the plurality of pixels in the depth image. The marking image may represent potential target objects in the depth image. The method may also include determining a locating coordinate of the target object under the target coordinate system according to the marking image.

Abstract: There is provided a method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images. The 2D medical images are uploaded by an end-user via a Web Application and sent to a server. The server processes the 2D medical images and automatically generates a 3D printable model of a patient specific anatomic feature from the 2D medical images using a segmentation technique. The 3D printable model is 3D printed as a 3D physical model such that it represents a 1:1 scale of the patient specific anatomic feature. The method includes the step of automatically identifying the patient specific anatomic feature.

Abstract: Aspects of the technology described herein relate to automatically calculating and displaying a prediction of a collective opinion of a group of individuals regarding imaging data and/or an output based on the imaging data. In some embodiments, the prediction may be a prediction of the collective opinion of a group of individuals regarding the usability of imaging data, regarding a segmentation of an image, or regarding a measurement performed based on the imaging data.

Abstract: A dynamic anatomic atlas is disclosed, comprising static atlas data describing atlas segments and dynamic atlas data comprising information on a dynamic property which information is respectively linked to the atlas segments.

Abstract: Apparatus and methods for extraction and calculation of multi-person performance metrics in a three-dimensional space. An example apparatus includes a detector to identify a first subject in a first image captured by a first image capture device based on a first set of two-dimensional kinematic keypoints in the first image, the two-dimensional kinematic keypoints corresponding to a joint of the first subject, the first image capture device associated with a first view of the first subject, a multi-view associator to verify the first subject using the first image and a second image captured by a second image capture device, the second image capture device associated with a second view of the first subject, the second view different than the first view, and a keypoint generator to generate three-dimensional keypoints for the first subject using the first set of two-dimensional kinematic keypoints.

Abstract: Methods and apparatus for determining a trajectory of a axisymmetric object in 3-D physical space using a digital camera which records 2-D image data are described. In particular, based upon i) a characteristic length of the axisymmetric object, ii) a physical position of the camera determined from sensors associated with the camera (e.g., accelerometers) and iii) captured 2-D digital images from the camera including a time at which each image is generated relative to one another, a position, a velocity vector and an acceleration vector can be determined in three dimensional physical space for axisymmetric object objects as a function of time. In one embodiment, the method and apparatus can be applied to determine the trajectories of objects in games which utilize axisymmetric object objects, such as basketball, baseball, bowling, golf, soccer, rugby or football.

Abstract: A speed estimation system includes: a detection module configured to determine bounding boxes of an object moving on a surface in images, respectively, captured using a camera; a solver module configured to, based on the bounding boxes, determine a homography of the surface by solving an optimization problem, where the solver module is not trained; and a speed module configured to, using the homography, determine a speed that the object is moving on the surface.

Abstract: A processor-implemented object tracking method includes: setting a suppressed region in a template image based on a shape of a target box of the template image; refining a template feature map of the template image by suppressing an influence of feature data corresponding to the suppressed region in the template feature map; and tracking an object by determining a bounding box corresponding to the target box in a search image based on the refined template feature map.

Abstract: Provided is a method and apparatus for eye tracking. An eye tracking method includes detecting an eye area corresponding to an eye of a user in a first frame of an image; determining an attribute of the eye area; selecting an eye tracker from a plurality of different eye trackers, the eye tracker corresponding to the determined attribute of the eye area; and tracking the eye of the user in a second frame of the image based on the selected eye tracker, the second frame being subsequent to the first frame.

Abstract: An information processing obtains a first image which is obtained by using a first camera to capture a three-dimensional space; obtains map information that is generated based on a second transformed image obtained by using second transformation information to geometrically transform a second image which has been captured by using a second camera to capture the three-dimensional space; generates a first transformed image by using first transformation information to geometrically transform the first image; and collates the map information and the first transformed image. The first transformation information and the second transformation information are set so that a geometric correspondence relationship between the three-dimensional space and the first transformed image and a geometric correspondence relationship between the three-dimensional space and the second transformed image will have a common geometric correspondence relationship.

Abstract: Some implementations relate to methods and computer-readable media to detect inauthentic textures in a virtual environment. In some implementations, a method includes receiving a plurality of two-dimensional (2D) polygons associated with a texture for a three-dimensional (3D) virtual object. The method further includes combining portions of two or more 2D polygons from the plurality of 2D polygons based on a pose or shape of the 3D virtual object to obtain one or more combined 2D polygons, calculating a respective hash value for each of the combined 2D polygons, determining whether there is a match between at least one hash value of the respective hash values and a hash value of at least one reference 2D polygon associated with an authentic object, classifying the texture as an inauthentic texture if it is determined that there is the match, else classifying the texture as an authentic texture.

Abstract: In one implementation, a method of activating a depth sensor is performed by a device including a depth sensor including a plurality of depth sensor elements, a display, one or more processors, and non-transitory memory. The method includes obtaining content to be displayed on the display in association with a physical environment. The method includes selecting a subset of the plurality of depth sensor elements. The method includes activating the subset of the plurality of depth sensor elements to obtain a depth map of the physical environment. The method includes displaying, on the display, at least a portion of the content based on the depth map of the physical environment.

Abstract: The embodiments herein provide a method and a device for the acquisition of three-dimensional information of body parts. The method includes a step of processing an image of an object being exposed to a lighting condition or a sequence of lighting conditions adapted to extract at least two types of information selectable from a group. The group includes a silhouette of the object, a color of the object, a surface orientation of the object, and multi-spectral information of the object.

Abstract: One aspect relates to a computer-implemented method for determining a quasi-rotation-invariant shape descriptor of point cloud data in an automotive system for monitoring the environment of a vehicle. In order to determine the shape descriptor, a method of determining a central point of a point cloud data is performed multiple times, each time using different values for one or more starting parameters. The method may yield different central points depending on the selected values for the one or more starting parameters. A regression line is calculated for the plurality of central points such that the shape descriptor is determined based on a base form of the plurality of central points.

Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.

Abstract: A three-dimensional object reconstruction method, applied to a terminal device or a server, is provided. The method includes obtaining a plurality of video frames of an object; determining three-dimensional location information of key points of the object in the plurality of video frames and physical meaning information of the key points, the physical meaning information indicating respective positions of the object; determining a correspondence between the key points having the same physical meaning information in the plurality of video frames; and generating a three-dimensional object according to the correspondence and the three-dimensional location information of the key points.

Abstract: An object of the present invention is to provide a ground boundary estimation method, a ground boundary estimation apparatus, and a program that can acquire the elevation of the ground boundary of the electrical pole quickly and accurately even when the base of the electrical pole is shielded by any shield at observation of the electrical pole. According to the ground boundary estimation method of the present invention, a difference in height between the columnar shape of a three-dimensional model of a columnar object such as an observed electrical pole and a standard shape of the columnar object at a position in which the three-dimensional model and the standard shape are equal to each other in the horizontal dimension is determined, and a penetration depth prescribed by the standard is subtracted from the difference in height, to find a height of a shielded portion of the ground boundary of the columnar object.

Abstract: A liquid level detection system of detecting a target container includes a main body, an optical sensor, a fan and an operational processor. The main body has a supporting platform whereon the target container is disposed. The optical sensor is disposed above the supporting platform and adapted to output a detection image containing the target container. The fan is disposed on the main body and faces the supporting platform. The operational processor is electrically connected to the optical sensor, and adapted to analyze the detection image generated within an operation period of the fan and further to acquire an effective feature of the target container inside the detection image.

Abstract: An information processing apparatus (2000) includes a detection unit (2020), a state estimation unit (2040), and a height estimation unit (2080). The detection unit (2020) detects a target person from a video frame. The state estimation unit (2040) estimates a state of the detected target person. The height estimation unit (2080) estimates a height of the person on the basis of a height of the target person in the video frame in a case where the estimated state satisfies a predetermined condition.

Abstract: Imaging systems, including radio frequency, microwave and millimeter-wave arrangements, and related methods are described. According to one aspect, an imaging system includes an antenna array, a position capture system configured to generate position information indicative of locations of one of the antenna array and the target at the first and second moments in time, and wherein the one of the antenna array and the target move between the first and second moments in time, a transceiver configured to control the antenna array to emit electromagnetic energy towards the target and to generate an output that is indicative of the received electromagnetic energy, a data acquisition system configured to generate radar data, processing circuitry configured to process the position information and the radar data to generate image data regarding the target, and an interface configured to use the image data to generate visual images regarding the target.

Abstract: A moving body includes processing circuitry. The processing circuitry is configured to collect an external image of the moving body from an external sensor and collect information associated with an inner state of the moving body from an internal sensor. The processing circuitry is configured to determine whether or not to adopt the external image collected by the external sensor as a first image for estimating a position of the moving body, based on the information associated with the inner state of the moving body collected by the internal sensor. The processing circuitry is configured to estimate a position of the moving body by comparing the first image and a second image associated with a collection position of the first image.

Abstract: A networked computer system for recognizing objects in video images is described herein. The networked computer system includes a user display device, a camera, and an object recognition system. The camera includes an imaging device having a 360° field-of-view and a global positioning system (GPS) device. The object recognition system includes a processor programmed to execute an algorithm including receiving live-stream video images from the camera, detecting an object of interest within the live-stream video images, determining pixel coordinates associated with a center of the detected object of interest, receiving the geographic location data from the camera, determining a geographic location of the object of interest based on the determined pixel coordinates and the geographic location of the camera, and displaying the live-stream video images on the user display device including a visual indicator of the object of interest and the determined geographic location of the object of interest.

Abstract: Head pose information may be determined using information describing a fixed gaze and image data corresponding to a user's eyes. The head pose information may be determined in a manner that is disregards facial features with the exception of the user's eyes. The head pose information may be usable to interact with a user device.

Abstract: The present disclosure provides a method and an apparatus for determining an attitude angle of a camera, capable of improving the accuracy of the attitude angle of the camera, and in turn the accuracy of the attitude of the camera that is obtained based on the attitude angle of the camera. The present disclosure can also improve the accuracy of object distance measurement and vehicle positioning based on the attitude angle of the camera. In the method for determining an attitude angle of a camera, the camera is fixed to one and the same rigid object in a vehicle along with an Inertial Measurement Unit (IMU).

Abstract: An embodiment mobility device includes a position detector configured to detect a first current position of the mobility device, a display configured to display position information of the mobility device, and a controller configured to set the first current position of the mobility device detected by the position detector as first position information, identify an augmented reality (AR) marker in a predetermined range, based on the first position information, determine a second current position of the mobility device based on the identified AR marker, and set the second current position of the mobility device determined based on the identified AR marker as second position information, and determine final position information of the mobility device by applying the second position information to the first position information.

Abstract: An image acquisition method, an image acquisition device and a storage medium are provided. The method includes: acquiring a preview image collected by a camera; detecting a target area in the preview image based on a preset composition model; and in response to detecting the target area, acquiring an image including the target area as a target image.

Abstract: An example trailer monitoring system includes a trailer monitoring unit (TMU) that has an image capture arrangement disposed within the TMU, the image capture arrangement to capture first image data, and an accelerometer carried by the TMU, the accelerometer to generate acceleration data of the TMU. The system also has one or more processors configured to access the acceleration data and configured to compare the acceleration data to a reference acceleration data range to determine if the acceleration data is within the reference acceleration range, in response to the acceleration data being outside the reference acceleration data range, the one or more processors are to record an impact event associated with the TMU being impacted, and in response to the acceleration data being outside the reference acceleration data range, the one or more processors are to generate a message associated with the impact event.

Abstract: There is provided a system and method of re-projecting and combining sensor data of a scene from a plurality of sensors for visualization. The method including: receiving the sensor data from the plurality of sensors; re-projecting the sensor data from each of the sensors into a new viewpoint; localizing each of the re-projected sensor data; combining the localized re-projected sensor data into a combined image; and outputting the combined image. In a particular case, the receiving and re-projecting can be performed locally at each of the sensors.

Abstract: Provided are methods for deep learning-based camera calibration, which can include receiving first and second images captured by a camera, processing the first image using a first neural network to determine a depth of the first image, processing the first image and the second image using a second neural network to determine a transformation between a pose of the camera for the first image and a pose of the camera for the second image, generating a projection image based on the depth of the first image, the transformation of the pose of the camera, and intrinsic parameters of the camera, comparing the second image and the projection image to determine a reprojection error, and adjusting at least one of the intrinsic parameters of the camera based on the reprojection error. Systems and computer program products are also provided.

Abstract: The present application discloses an image projection method, apparatus, device and storage medium and relates to the field of intelligent transportation, and the specific implementation thereof is: acquiring a first camera coordinate of an area to be calibrated in a camera coordinate system of an AR camera on a vehicle, where the area to be calibrated is located within a photographing range of the AR camera; acquiring a relative conversion relationship between a first extrinsic parameter matrix of the AR camera and a second extrinsic parameter matrix of a head-up display on the vehicle; determining, according to the first camera coordinate and the relative conversion relationship, a second camera coordinate of a projection symbol corresponding to the area to be calibrated in a coordinate system of the head-up display; and controlling, according to the second camera coordinate, the head-up display to project an image including the projection symbol.

Abstract: A method for decoding image content from an encoded bitstream including a plurality of blocks includes: dividing a block including one or more components of the image content into N single samples and M sample groups corresponding to one of the components, where N and M are greater than or equal to one; decoding each of the N single samples using a symbol variable length code to generate one or more decoded single samples; decoding each of the M sample groups using a common prefix entropy code to generate one or more decoded sample groups, each of the M sample groups including a variable length prefix and one or more fixed length suffixes representing a plurality of samples; concatenating the decoded single samples and the decoded sample groups into a block of residuals; and reconstructing image content based on previously reconstructed neighboring blocks and the block of residuals.

Abstract: A video and audio presentation device configured to present video and audio for sports training with less delay in physical reaction is provided.

Abstract: A system and method for privacy protection in vision systems that can include collecting image data from an environment; collecting spatial information corresponding to the image data; selecting a sanitization image region in the image data based at least in part on the spatial information; and applying image sanitization to the sanitization image region thereby generating sanitized image data.

Abstract: Disclosed are systems, methods, and computer-readable storage media to modify image content. One aspect includes identifying, by one or more electronic hardware processors, an image and content within the image, determining, by the one or more electronic hardware processors, a sky region of the image, determining, by the one or more electronic hardware processors, whether the content within the image is located within the sky region of the image, and in response to the content being within the sky region of the image, modifying, by the one or more electronic hardware processors, the content based on fractal Brownian motion.

Abstract: Anisotropic texture filtering applies a texture at a sampling point in screen space. Calculated texture-filter parameters configure a filter to perform filtering of the texture for the sampling point. The texture for the sampling point is filtered using a filtering kernel having a footprint in texture space determined by the texture-filter parameters. Texture-filter parameters are calculated by generating a first and a second pair of screen-space basis vectors being rotated relative to each other. First and second pairs of texture-space basis vectors are calculated that correspond to the first and second pairs of screen-space basis vectors transformed to texture space under a local approximation of a mapping between screen space and texture space. An angular displacement is determined between a selected pair of the first and second pairs of screen-space basis vectors and screen-space principal axes of a local approximation of the mapping that indicate the maximum and minimum scale factors of the mapping.

Abstract: A method generates map visualizations with multiple map layers. A user selects a data source with geographic data. A device displays a data visualization user interface, including a schema information region with data fields, and shelf regions that defining characteristics for a data visualization. The user selects a first geographic data, and the user interface generates a map data visualization using coordinates associated with the first geographic data field. The visualization includes a first plurality of data marks in a first layer. The user selects a second geographic data field. In response, the user interface displays a new layer icon. Upon activation of the new layer icon by the second geographic data field, the user interface superimposes a second layer over the existing map data visualization to form an updated map data visualization. The second layer includes a second plurality of data marks corresponding to the second geographic data field.

Abstract: Various implementations disclosed herein include devices, systems, and methods for modifying character motion for 3D animated assets (e.g., modifying character motions). In some implementations, an object to be animated is identified, where the object is a part of a three dimensional (3-D) digital model. In some implementations, a motion descriptor is identified that includes path-generating components that generate a preliminary motion path for animation of the object. The motion descriptor is modified to generate a modified motion path, where the motion descriptor is modified by deforming at least one path-generating component of the motion descriptor, and the object is animated based on the modified motion path. In some implementations, the modified motion path is transferred to another 3D animated asset (e.g., the same or a different type of 3D animated asset).

Abstract: An animation system wherein scanned facial expressions are processed to form muscle models based on live actors combines muscle models over a plurality of live actors to form a facial rig usable for generating expressions based on specification of a strain vector and a control vector of a muscle model for varying characters corresponding to live actors.

Abstract: A method for providing a relightable avatar of a subject to a virtual reality application is provided. The method includes retrieving multiple images including multiple views of a subject and generating an expression-dependent texture map and a view-dependent texture map for the subject, based on the images. The method also includes generating, based on the expression-dependent texture map and the view-dependent texture map, a view of the subject illuminated by a light source selected from an environment in an immersive reality application, and providing the view of the subject to an immersive reality application running in a client device. A non-transitory, computer-readable medium storing instructions and a system that executes the instructions to perform the above method are also provided.

Abstract: An animation system is provided for generating an animation control rig for character development, configured to manipulate a skeleton of an animated character. Hierarchical representation of puppets includes groups of functions related in a hierarchy according to character specialization for creating the animated rig are derived using base functions of a core component node. The hierarchical nodes may include an archetype node, at least one appendage node, and at least one feature node. In some implementations, portions of a hierarchical node, including the functions from the core component node, may be shared to generate different animation rigs for a variety of characters. In some implementations, portions of a hierarchical node, including the component node functions, may be reused to build similar appendages of a same animation rig.

Abstract: Disclosed is an image processing apparatus for supplying display information indicating a three-dimensional image to a recording device including a discharge section that discharges liquid to an object having a three-dimensional shape to form a three-dimensional image on the object. The image processing apparatus includes an obtaining section that obtains virtual space information and a generating section that generates the display information based on the virtual space information. The virtual space information indicates a virtual image in which the three-dimensional image is represented in a three-dimensional virtual space, and a virtual discharge section, in which the discharge section is represented in the virtual space. The relative positional relationship in the virtual space between the virtual image and the virtual discharge section indicated by the virtual space information corresponds to the relative relationship between the three-dimensional image and the discharge section.

Abstract: Training deep neural networks requires a large amount of labeled training data. Conventionally, labeled training data is generated by gathering real images that are manually labelled which is very time-consuming. Instead of manually labelling a training dataset, domain randomization technique is used generate training data that is automatically labeled. The generated training data may be used to train neural networks for object detection and segmentation (labelling) tasks. In an embodiment, the generated training data includes synthetic input images generated by rendering three-dimensional (3D) objects of interest in a 3D scene. In an embodiment, the generated training data includes synthetic input images generated by rendering 3D objects of interest on a 2D background image. The 3D objects of interest are objects that a neural network is trained to detect and/or label.

Abstract: A GPU includes shader cores and a shader warp packer unit. The shader warp packer unit may receive a first primitive associated with a first partially covered quad, and a second primitive associated with a second partially covered quad. The shader warp packer unit may determine that the first partially covered quad and the second partially covered quad have non-overlapping coverage. The shader warp packer unit may pack the first partially covered quad and the second partially covered quad into a packed quad. The shader warp packer unit may send the packed quad to the shader cores. The first partially covered quad and the second partially covered quad may be spatially disjoint from each other. The shader cores may receive and process the packed quad with no loss of information relative to the shader cores individually processing the first partially covered quad and the second partially covered quad.

Abstract: A technique for compressing an original image is disclosed. According to the technique, an original image is obtained and a delta-encoded image is generated based on the original image. Next, a segregated image is generated based on the delta-encoded image and then the segregated image is compressed to produce a compressed image. The segregated image is generated because the segregated image may be compressed more efficiently than the original image and the delta image.