Abstract: A computing device spatially reconstructs a virtual feature surface in a mixed reality environment. The computing device detects addition of a raycast element to a virtual user space, maps multiple feature points detected from multiple video frames of a physical user space into a virtual user space, selecting at least three feature points from the multiple feature points that satisfy selection criteria applied in the virtual user space along a raycast axis of the raycast element in the virtual user space, and defines the virtual feature surface in the virtual user space using the at least three selected feature points. At least two of the at least three feature points are detected in different video frames.

Abstract: It is possible to determine a geometric transformation matrix representing geometric transformation between an input image and a template image with high precision. A geometric transformation matrix/inlier estimation section 32 determines a corresponding point group serving as inliers, and estimates the geometric transformation matrix representing the geometric transformation between the input image and the template image. A scatter degree estimation section 34 estimates scatter degree of the corresponding points based on the corresponding point group serving as inliers. A plane tracking convergence determination threshold calculation section 36 calculates a threshold used in convergence determination when iterative update of the geometric transformation matrix in a plane tracking section 38 is performed based on the estimated scatter degree.

Abstract: A model-based method for quantifying a specimen. The method includes providing a specimen, capturing images of the specimen while illuminated by multiple spectra at different nominal wavelengths, and exposures, and classifying the specimen into various class types comprising one or more of serum or plasma portion, settled blood portion, gel separator (if used), air, tube, label, or cap; and quantifying of the specimen. Quantifying includes determining one or more of: a location of a liquid-air interface, a location of a serum-blood interface, a location of a serum-gel interface, a location of a blood-gel interface, a volume and/or a depth of the serum or plasma portion, or a volume and/or a depth of the settled blood portion. Quality check modules and specimen testing apparatus adapted to carry out the method are described, as are other aspects.

Abstract: Methods and systems are provided which relate to the planning and delivery of radiation treatments by modalities which involve moving a radiation source along a trajectory relative to a subject while delivering radiation to the subject. An artificial intelligence (AI) agent trained using reinforcement learning (and/or some other suitable form of machine learning) is used to control the radiation delivery parameters in effort to achieve desired delivery of radiation therapy. In some embodiments, the AI agent selects suitable control steps (e.g. radiation delivery parameters for particular time steps), while accounting for patient motions, difference(s) in patient anatomical geometry and/or the like.

Abstract: A method of processing image data in a connectionist network includes: determining, a plurality of offsets, each offset representing an individual location shift of an underlying one of the plurality of output picture elements, determining, from the plurality of offsets, a grid for sampling from the plurality of input picture elements, wherein the grid comprises a plurality of sampling locations, each sampling location being defined by means of a respective pair of one of the plurality of offsets and the underlying one of the plurality of output picture elements, sampling from the plurality of input picture elements in accordance with the grid, and transmitting, as output data for at least a subsequent one of the plurality of units of the connectionist network, a plurality of sampled picture elements resulting from the sampling, wherein the plurality of sampled picture elements form the plurality of output picture elements.

Abstract: Systems and methods for detecting patterns in data from a time-series are provided. In one implementation, a method for pattern detection includes obtaining data in a time-series and creating one-dimensional or multi-dimensional windows from the time-series data. The one-dimensional or multi-dimensional windows are created either independently or jointly with the time-series. The method also includes training a deep neural network with the one-dimensional or multi-dimensional windows utilizing historical and/or simulated data to provide a neural network model. Also, the method includes processing ongoing data with the neural network model to detect one or more patterns of a particular category in the ongoing data, and localizing the one or more patterns in time.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for image rendering. In one aspect, a method comprises receiving a plurality of observations characterizing a particular scene, each observation comprising an image of the particular scene and data identifying a location of a camera that captured the image. In another aspect, the method comprises receiving a plurality of observations characterizing a particular video, each observation comprising a video frame from the particular video and data identifying a time stamp of the video frame in the particular video. In yet another aspect, the method comprises receiving a plurality of observations characterizing a particular image, each observation comprising a crop of the particular image and data characterizing the crop of the particular image. The method processes each of the plurality of observations using an observation neural network to determine a numeric representation as output.

Abstract: A method of unsupervised learning of a metric representation and a corresponding system for a mobile device determines a metric position information for a mobile device from an environmental representation. The mobile device comprises at least one sensor for acquiring sensor data and an odometer system configured to acquire displacement data of the mobile device. An environmental representation is generated based on the acquired sensor data by applying an unsupervised learning algorithm. The mobile device moves along a trajectory and the displacement data and the sensor data are acquired while the mobile device is moving along the trajectory. A set of mapping parameters is calculated based on the environmental representation and the displacement data. A metric position estimation is determined based on a further environmental representation and the calculated set of mapping parameters.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network that is configured to process an input observation to generate a latent representation of the input observation. In one aspect, a method includes: obtaining a sequence of observations; for each observation in the sequence of observations, processing the observation using the encoder neural network to generate a latent representation of the observation; for each of one or more given observations in the sequence of observations: generating a context latent representation of the given observation; and generating, from the context latent representation of the given observation, a respective estimate of the latent representations of one or more particular observations that are after the given observation in the sequence of observations.

Abstract: This disclosure describes interactive data processing systems configured to facilitate selection by a human associate of tentative results generated by an automated system from sensor data. In one implementation, an event may take place in a materials handling facility. The event may comprise a pick or place of an item from an inventory location, movement of a user, and so forth. The sensor data associated with the event is processed by an automated system to determine tentative results associated with the event. In some situations, an uncertainty may exist as to which of the tentative results accurately reflects the actual event. The system may then determine whether the event is to be merged with one or more temporally and spatially proximate events and, if so, the sensor data and tentative results for the merged event is sent to a human associate. The associate may select one of the tentative results.

Abstract: The disclosure relates to PET imaging systems and methods. The systems may obtain a plurality of PET images of a subject and a CT image acquired by performing a spiral CT scan on the subject. Each gated PET image may include a plurality of sub-gated PET images. The CT image may include a plurality of sub-CT images each of which corresponds to one of the plurality of sub-gated PET images. The systems may determine a target motion vector field between a target physiological phase and a physiological phase of the CT image based on the plurality of sub-gated PET images and the plurality of sub-CT images. The systems may reconstruct an attenuation corrected PET image corresponding to the target physiological phase based on the target motion vector field, the CT image, and PET data used for the plurality of gated PET images reconstruction.

Abstract: This application discloses a video image anti-shake method and a terminal, and relates to the field of image processing, to implement compensation for translational shake in a Z direction. A video image anti-shake method includes: turning on, by a terminal, a camera lens, and photographing a video image by using the camera lens; detecting, by the terminal, shake on an X-axis, a Y-axis, and a Z-axis during photographing, where the Z-axis is an optical axis of the camera lens, the X-axis is an axis perpendicular to the Z-axis on a horizontal plane, and the Y-axis is an axis perpendicular to the Z-axis on a vertical plane; and performing, by the terminal, anti-shake processing on the video image based on the shake on the X-axis, the Y-axis, and the Z-axis. Embodiments of this application are applied to video image anti-shake.

Abstract: An electronic device having a neural network framework for estimating optical flow is provided. The electronic device is connected to an image acquiring unit, which acquires images to be analyzed. The electronic device includes a storage unit, a feature extraction unit, an optical flow estimation unit and a refining unit. The storage unit stores a feature extraction module. The feature extraction unit is connected to the image acquiring unit and the storage unit. The optical flow estimation unit is connected to the feature extraction unit to generate an estimated optical flow. The refining unit is connected to the optical flow estimation unit to input the estimated optical flow to a refining module to obtain an estimated optical flow result. A method for estimating optical flow is also provided to reduce the number of training parameters required for estimating optical flow, thereby reducing a training time and improving training stability.

Abstract: A head-mounted device (HMD) is configured to perform depth detection with a stereo camera pair comprising a first camera and a second camera, both of which are configured to detect/capture visible light and IR light. The fields of view for both of the cameras overlap to form an overlapping field of view. The HMD also includes an IR dot-pattern illuminator that is mounted on the HMD with the cameras and that is configured to emit an IR dot-pattern illumination. The IR dot-pattern illuminator emits a dot-pattern illumination that spans at least a part of the overlapping field of view. The IR dot-pattern illumination adds texture to objects in the environment and enables the HMD to determine depth for those objects, even if they have textureless/smooth surfaces.

Abstract: Some embodiments are directed to an image director of a patient monitoring system to obtain calibration images of a calibration sheet or other calibration object at various orientations and locations. The images are then stored and processed to calculate camera parameters defining the location and orientation of the image detector and identifying internal characteristics of the image detector, and the information are stored. The patient monitoring system can be re-calibrated by using the image detector to obtain an additional image of a calibration sheet or calibration object. The additional image and the stored camera parameters are then used to detect any apparent change in the internal characteristics of the image detector (10)(S6-4).

Abstract: A head-mounted device (HMD) is configured to perform depth detection with a stereo camera pair comprising a first camera and a second camera, both of which are configured to detect/capture visible light and IR light. The fields of view for both of the cameras overlap to form an overlapping field of view. The HMD also includes an IR dot-pattern illuminator that is mounted on the HMD with the cameras and that is configured to emit an IR dot-pattern illumination. The IR dot-pattern illuminator emits a dot-pattern illumination that spans at least a part of the overlapping field of view. The IR dot-pattern illumination adds texture to objects in the environment and enables the HMD to determine depth for those objects, even if they have textureless/smooth surfaces.

Abstract: Systems and methods for using quantitative ultrasound (“QUS”) techniques to generate imaging biomarkers that can be used to assess a prediction of tumor response to different chemotherapy treatment regimens are provided. For instance, the imaging biomarkers can be used to subtype tumors that have resistance to certain chemotherapy regimens prior to drug exposure. These imaging biomarkers can therefore be useful for predicting tumor response and for assessing the prognostic value of particular treatment regimens.

Abstract: Techniques for active learning-based data labeling are described. An active learning-based data labeling service enables a user to build and manage large, high accuracy datasets for use in various machine learning systems. Machine learning may be used to automate annotation and management of the datasets, increasing efficiency of labeling tasks and reducing the time required to perform labeling. Embodiments utilize active learning techniques to reduce the amount of a dataset that requires manual labeling. As subsets of the dataset are labeled, this label data is used to train a model which can then identify additional objects in the dataset without manual intervention. The process may continue iteratively until the model converges. This enables a dataset to be labeled without requiring each item in the data set to be individually and manually labeled by human labelers.

Abstract: A system and method are provided for capturing an image with correct skin tone exposure. In use, one or more faces are detected having threshold skin tone within a scene. Next, based on the detected one or more faces, the scene is segmented into one or more face regions and one or more non-face regions. A model of the one or more faces is constructed based on a depth map and a texture map, the depth map including spatial data of the one or more faces, and the texture map includes surface characteristics of the one or more faces. The one or more images of the scene are captured based on the model. Further, in response to the capture, the one or more face regions are processed to generate a final image.

Abstract: A device includes an image sensor and an array of optical channels, each optical channel including an optic for projecting a partial field of view of a total field of view onto an image sensor area of the image sensor. A first optical channel of the array is configured to image a first partial field of view of the total field of view. A second optical channel of the array is configured to image a second partial field of view of the total field of view. The device includes a calculating unit configured to obtain image information of the first and second partial fields of view on the basis of the imaged partial fields of view, and to obtain image information of the total field of view, and to combine the image information of the partial fields of view with the image information of the total field of view so as to generate combined image information of the total field of view.

Abstract: An image processing apparatus includes a printer that prints an image on a sheet, a scanner that reads an image on a sheet, and one or more controllers configured to cause the scanner to read an image on a sheet, to cause a display to display the image, to receive an instruction for adopting an image serving as a candidate for a correct image from the displayed image, to generate the correct image based on the image serving as the candidate, to register the correct image, and to cause the scanner to read an image printed on a sheet and to verify the printed image based on the read image and the registered correct image. When a defective image is in the read image, the display displays the defective image in which a defective area is emphasized and the defective image in which the defective area is not emphasized.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to analyze graph information. An example apparatus includes a graph computational processor. The example graph computational processor is configured to analyze a first graph with respect to a second graph to identify a third graph within the first graph by: matching a first triplet from the first graph to a second triplet from the second graph by comparing each node and connecting edge included in each triplet; and generating the third graph by adding, when the first triplet matches the second triplet, the first triplet to a subgraph output set forming the third graph. The example graph computational processor of is configured to identify an additional node in the first graph based on the third graph and generate an output based on the additional node.

Abstract: Colored three-dimensional digital model generation techniques and systems are described. In one example, scanning techniques are employed by a scanning system that scans a physical object while disposed within packaging to form a three-dimension digital model. A model coloring system is employed to color the three-dimensional digital model. A two-dimensional digital image is employed that captures the same or similar physical object. In one example, features of the model are matched to the image. This is then used to align a viewing perspective with respect to the model with a viewing perspective of the object within the digital image, e.g., to find which “view” of the model corresponds with the image. The color is then applied from the digital image to the model, e.g., from pixels of the image to corresponding points in the model.

Abstract: Embodiments of the present disclosure provides a method and apparatus for constructing a map. The method may include: determining pose information of each panoramic image frame from a panoramic image sequence of a target area, and determining a perspective image sequence from each panoramic image frame; determining a feature track corresponding to the panoramic image sequence based on perspective image sequences corresponding to adjacent panoramic image frames; and constructing a visual map of the target area based on the feature track and the pose information of each panoramic image frame.

Abstract: An example disclosed method includes (i) transmitting a first point cloud to a client, wherein the first point cloud corresponds to a reference point cloud, (ii) receiving a second point cloud, and (iii) hierarchically determining changes in the second point cloud from the reference point cloud, wherein hierarchically determining the changes includes (a) identifying first areas in the second point cloud that have changed from the reference point cloud, and (b) for a first area having a highest priority, determining a first rigid 3D transformation that approximates a first change from the reference point cloud, and if the first rigid 3D transformation cannot be determined, further determining first points to be used to modify the reference point cloud, wherein the first points are representative of the first change.

Abstract: Geospatial data is gathered for generation of a geodatacube encompassing data from multiple geospatial data sets for efficient processing and optimization. A method for gathering, storing and processing geospatial data includes identifying a plurality of geospatial data sets for intake, each defining a geospatial data parameter. For each geospatial data set, a plurality of subregions is defined such that each subregion corresponds to a portion of the geographic entity having the same value for the data parameter defined by the respective geospatial data set. In other words, subdividing the geographic entity along demarcations defined by variances in the data parameter(s) defined by the geospatial data set. A number of geospatial data sets for intake are arranged into layers, where each layer defines the data parameter for the respective subregions of the geographic entity. A partition defining polygons common to all layers represents a union of the subregions.

Abstract: Image signal processing includes generating an exposure compensated image based on a gain value applied to an exposure level of a first image and a gain value applied to an exposure level of a second image. The gain value may be progressively increased from an approximate center of the first image to an edge of the first image to a common exposure level. The gain value may be progressively decreased from an approximate center of the second image to an edge of the second image to the common exposure level. Gain values may be scaled on each color channel for a pixel based on a saturation level of the pixel.

Abstract: Event ordering is provided in a distributed file system. For instance, events are generated that are associated with an object collected from nodes in the distributed file system, and an event loop indicates causal dependencies among the events, and comprises one or more reliable edges and unreliable edges. Degrees of reliability of the unreliable edges in the event loop are determined, and then at least one unreliable edge is removed from the event loop based on the determined degrees of reliability. Causal dependencies among the events in the distributed file system are analyzed by using a statistical method, and the most unreliable edge in the event loop can be removed by computing a degree of reliability of each unreliable edge, thereby avoiding the occurrence of the event loop.

Abstract: A prediction apparatus includes a learning section that performs machine learning in which, with respect to a combination of different types of captured images obtained by imaging the same subject, one captured image is set to an input and another captured image is set to an output to generate a prediction model; and a controller that performs a control for inputting a first image to the prediction model as an input captured image and outputting a predicted second image that is a captured image having a type different from that of the input captured image.

Abstract: Technologies for determining the accuracy of three-dimensional models include a device having circuitry to obtain two-dimensional images of an anatomical object (e.g., a bone of a human joint), to obtain a candidate three-dimensional model of the anatomical object, and to produce two-dimensional silhouettes of the candidate three-dimensional model. The circuitry is also to apply an edge detection algorithm to the two-dimensional images to produce corresponding edge images and to compare the two-dimensional silhouettes to the edge images to produce a score indicative of an accuracy of the candidate three-dimensional model.

Abstract: A method of estimating a self-location of a vehicle includes obtaining an omnidirectional image by using an omnidirectional camera photographing a ground around a driving vehicle at a current location of the driving vehicle, estimating the current location of the driving vehicle on the basis of a global positioning system (GPS) satellite signal received from a satellite, searching a satellite image database storing a satellite image obtained by photographing the ground with the satellite to determine candidate satellite images corresponding to the estimated current location of the driving vehicle, comparing the omnidirectional image with each of the determined candidate satellite images to determine a candidate satellite image having a highest similarity to the omnidirectional image from among the determined candidate satellite images, and finally estimating the current location of the driving vehicle by using a location measurement value mapped to the determined candidate satellite image.

Abstract: A georeferenced trajectory estimation system receives data generated by vehicle sensors from a fleet of vehicles and identifies sets of sensor measurements for a geographic region taken at different times. The sets of sensor measurements include environment geometry data and unaligned trajectory data in local coordinate frames. The georeferenced trajectory estimation system aligns the environment geometry data between sets of sensor measures, and, based on the alignment of the environment geometry data, transforms the identified corresponding trajectory data into a common coordinate frame.

Abstract: Systems, methods, and non-transitory computer readable media are provided for visually presenting geospatial information. An information request for an area may be received. The area may include one or more predefined regions. The predefined region(s) may be subdivided into one or more levels of predefined sub-regions. Information for the area may be accessed. The information for the area may include region information for the predefined region(s) or sub-region information for the predefined sub-regions. A response to the information request may be determined based on the region information or the sub-region information. The response may enable a visual presentation of (1) the information for the area, and (2) one or more geographical boundaries corresponding to the area.

Abstract: The present technique relates to an image processing apparatus, an image processing method, and a program that can easily execute a stitching process. Provided are: an image generation unit that generates a first reference image regarding a first imaging region on the basis of a plurality of first images regarding the first imaging region and that generates a second reference image regarding a second imaging region at least partially overlapping with the first imaging region on the basis of a plurality of second images regarding the second imaging region; and a processing unit that generates positioning information indicating a correspondence between the first imaging region and the second imaging region on the basis of the first reference image and the second reference image. The present technique can be applied to, for example, an image processing apparatus that executes a stitching process of a plurality of images.

Abstract: Disclosed are a method for updating a neural network and an electronic device. The method includes: inputting a first image set having tag information into a first depth neural network, and determining a cross entropy loss value of the first image set by using the first depth neural network; inputting a second image set having no tag information separately into the first depth neural network and a second depth neural network, and determining a consistency loss value of the second image set, the first depth neural network and the second depth neural network having the same network structure; updating parameters of the first depth neural network based on the cross entropy loss value and the consistency loss value; and updating parameters of the second depth neural network based on the updated parameters of the first depth neural network.

Abstract: An object tracking device includes a superimposed image creation unit configured to create a plurality of superimposed images in which each of a plurality of non-tracking object images which do not include a tracking object image feature is superimposed on a tracking object section image which includes a tracking object image feature; a discriminator creation unit configured to learn at least one of an image feature and position information of the tracking object, based on the plurality of superimposed images to create a discriminator; and a tracking object specifying unit configured to specify at least one of the image feature and the position information of the tracking object in a tracked image including the respective image features of the tracking object and an obstacle, based on the discriminator and the tracked image.

Abstract: A reading device includes an emission unit that emits light; a first reflecting unit having a first reflecting surface that reflects the light emitted by the emission unit toward a document; a second reflecting unit having a second reflecting surface that reflects the light reflected by the first reflecting unit and specularly reflected by the document; a first support unit that supports the first reflecting unit and the second reflecting unit and fixes a relative position and a relative orientation between the first reflecting surface and the second reflecting surface; and a second support unit that supports the first support unit such that at least one of a position and an orientation of the first support unit is adjustable.

Abstract: In accordance with various embodiments of the present disclosure, topology data, machine performance data, and service performance data of at least one stack of a cloud computing system are received by a cityscape generator. The cityscape generator may then generate a three-dimensional cityscape including at least one neighborhood that represents the at least one stack of the cloud computing system, the at least one neighborhood includes a cluster of first nodes associated with compute resources of a frontend of the at least one stack, a cluster of second nodes associated with compute resources of a backend of the at least one stack, and a cluster of third nodes associated with compute resources of a database cluster of the at least one stack, the generation of the three-dimensional cityscape being based the topology data, the machine performance data, and the service performance data. The cityscape generator may then cause the display of the three-dimensional cityscape.

Abstract: In accordance with an aspect of the present disclosure, there is provided a method for processing image performed by image processing device for rendering an augmented reality image. The method comprises, acquiring a first real image corresponding to a first direction from the image processing device, acquiring a second real image corresponding to a second direction, different from the first direction, from the image processing device, determining reflectivity of a surface of a virtual object in the augmented reality image; and rendering, according to the reflectivity, the surface of the virtual object by using an environment texture, the environment texture generated based on the first real image and the second real image.

Abstract: Improved targeting of cranial therapy is provided by warping a general purpose brain atlas to a measured head shape of the patient. The resulting patient-specific transformation from brain atlas to patient's head allows one to estimate the location of brain features of the patient without any patient specific brain imaging. Such cost-effective targeting of brain features is especially useful for therapies like transcranial magnetic stimulation, where accuracy of targeting brain structures and session-to-session consistency are both important.

Abstract: In one aspect, in a magnetic resonance imaging system having a gradient coil array comprising a plurality of independent coils distributed about an enclosure, a method of applying currents to said coils is disclosed, which comprises defining a merit function for optimizing at least one feature of any of a magnetic field and an electric field generated by the coils, using a computer processor to optimize the merit function so as to determine an optimal current vector, wherein said element of the current vector provides a current value for application to one of said gradient coils, and applying the currents to said coils.

Abstract: Techniques are described for using computing devices to perform automated operations to control acquisition of images in a defined area, including obtaining and using data from one or more hardware sensors on a mobile device that is acquiring the images, analyzing the sensor data (e.g., in a real-time manner) to determine the geometric orientation of the mobile device in three-dimensional (3D) space, and using that determined orientation to control the acquisition of further images by the mobile device. In some situations, the determined orientation information may be used in part to automatically generate and display a corresponding GUI (graphical user interface) that is overlaid on and augments displayed images of the environment surrounding the mobile device during the image acquisition process, so as to control the mobile device's geometric orientation in 3D space.

Abstract: The present invention relates to a method for vectorising nodes within a plurality of 360 degree images. The method includes identifying a set of points of interest within a first 360 degree image of the plurality of 360 degree images; identifying a corresponding set of points of interest within a second 360 degree image of the plurality of 360 degree images; and calculating the 3D coordinates of the points of interest using triangulation of both sets of points of interest. A system and software are also disclosed.

Abstract: An information processing apparatus includes a receiver that receives an input image to be recognized and a processor configured to, by executing a program, align the input image with a template image in such a way as to match a recognition area of the input image and a recognition area defined on the template image, perform a process for recognizing the recognition area of the aligned input image, generate a check image including the template image and the aligned input image, and display the check image and a result of the process for recognizing the recognition area of the aligned input image such that a correspondence between the check image and the result is recognizable.

Abstract: The present principles relates to a method and device for reconstructing an HDR image by applying a reconstruction process on a SDR image whose the content is similar to the content of the HDR image but the dynamic range of the luminance values of said SDR image is lower than the dynamic range of the luminance values of said HDR image, said reconstruction process requiring parameters obtained from a bitstream. The method is characterized in that the method further comprises determining whether all the required parameters are available from the bitstream and recovering the lost or corrupted parameters from additional data, said reconstruction process further taking into account said recovered parameters.

Abstract: A computing device spatially reconstructs a virtual feature surface in a mixed reality environment. The computing device detects addition of a raycast element to a virtual user space, maps multiple feature points detected from multiple video frames of a physical user space into a virtual user space, selecting at least three feature points from the multiple feature points that satisfy selection criteria applied in the virtual user space along a raycast axis of the raycast element in the virtual user space, and defines the virtual feature surface in the virtual user space using the at least three selected feature points. At least two of the at least three feature points are detected in different video frames.

Abstract: Embodiments relate to methods for efficiently encoding sensor data captured by an autonomous vehicle and building a high definition map using the encoded sensor data. The sensor data can be LiDAR data which is expressed as multiple image representations. Image representations that include important LiDAR data undergo a lossless compression while image representations that include LiDAR data that is more error-tolerant undergo a lossy compression. Therefore, the compressed sensor data can be transmitted to an online system for building a high definition map. When building a high definition map, entities, such as road signs and road lines, are constructed such that when encoded and compressed, the high definition map consumes less storage space. The positions of entities are expressed in relation to a reference centerline in the high definition map. Therefore, each position of an entity can be expressed in fewer numerical digits in comparison to conventional methods.

Abstract: The present invention relates to vascular treatment outcome visualization. To provide an enhanced possibility to check that a vascular treatment has been correctly performed, it is proposed to provide (112) a first image data (114) of a region of interest of a vascular structure at a first point in time, and to provide (116) at least one second image data (118) of the region of interest of the vascular structure at a second point in time, wherein a vascular treatment has been applied to the vascular structure between the first point in time and the second point in time. Further, the first and the at least one second image data are combined (120) generating a joint outcome visualization image data (122) and the joint outcome visualization image data is displayed (124).

Abstract: A method for characterizing a pose estimation system includes: receiving, from a pose estimation system, first poses of an arrangement of objects in a first scene; receiving, from the pose estimation system, second poses of the arrangement of objects in a second scene, the second scene being a rigid transformation of the arrangement of objects of the first scene with respect to the pose estimation system; computing a coarse scene transformation between the first scene and the second scene; matching corresponding poses between the first poses and the second poses; computing a refined scene transformation between the first scene and the second scene based on coarse scene transformation, the first poses, and the second poses; transforming the first poses based on the refined scene transformation to compute transformed first poses; and computing an average rotation error and an average translation error of the pose estimation system based on differences between the transformed first poses and the second poses.

Abstract: A system for display and interaction includes an interface and a processor. The interface is configured to receive data from one or more sensors. The processor is configured to convert the data to a common synthetic data space; provide the common synthetic data space for display; and receive a command associated with an object represented in the common synthetic data space. In some embodiments, the processor is coupled to a memory that stores instructions for the processor.