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.

A computer model to identify a type of physical card is trained using simulated card images. The physical card may exist with various subtypes, some of which may not exist or be unavailable when the model is trained. To most robustly identify these subtypes, the training data set for the computer model includes simulated card images that are generated for the card type. The simulated card images are generated based on a semi-randomized background that varies in appearance, onto which an identifying marking of the card type is superimposed, such that the training data for the computer model includes additional randomized sample card images and ensure the model is robust to further variations in subtypes.

A device implementing the subject high bit-depth graphics compression may include at least one processor configured to receive pixel data for a pixel block, obtain endpoints of a first bit length based on the pixel data in the pixel block, quantize the endpoints to a second bit length smaller than the first bit length, select the quantized endpoints for pixel values in the pixel block, determine a weight for each pixel of the pixel block in each of a plurality of planes corresponding to the endpoints selected for the pixel block, and generate a compressed data block representative of the pixel block based at least on the endpoints for the pixel block and the weight for each pixel of the pixel block in each of the plurality of planes corresponding to the endpoints. A method and computer program product implementing the subject high bit-depth graphics compression is also provided.

The technology disclosed relates to generating automated test plan scripts. A selection of a first test plan to automate is received. Test scripts and data from a repository are retrieved and the test scripts and the data correspond to the first test plan. Test steps of the first test plan are performed. A prediction of a reusable component for a particular test step or test validation is provided for each of the test steps. A selection of at least one prediction for at least one of the test steps is received. An automated test plan script corresponding to the selection of the at least one prediction is generated.

The disclosure provides a method for generating training data and an electronic device. The method includes: obtaining an object model of a specific object; obtaining a first image when the object model is positioned at a first angle and a first silhouette corresponding to the first image; retrieving a first object image representing the specific object positioned at the first angle from the first image based on the first silhouette; embedding the first object image into a first background image to generate a first training image; generating a first labeled data of the first object image in the first training image; and defining the first training image and the first labeled data as a first training data of the specific object.

An example apparatus for tracking features in image data includes an image data receiver to receive initial image data corresponding to an image from a camera and store the image data a circular buffer. The apparatus also includes a feature detector to detect features in the image data. The apparatus further includes a feature sorter to sort the detected features to generate sorted feature points. The apparatus includes a feature tracker to track the sorted feature points in subsequent image data corresponding to the image received at the image data receiver. The subsequent image data is to replace the initial image data in the circular buffer.

To allow a better determination of an image of a different luminance dynamic range (in particular as characterised by a different maximum luminance a.k.a. peak brightness) than an input image, the present application teaches several variants of a luminance processor (501) arranged to calculate an output luminance of a pixel of an output image (Im_LDR; Im3000 nit) having a second luminance dynamic range characterized by a second peak brightness (PB_LDR; PB_MDR) from an input luminance of a spatially collocated pixel of an input image (MAST_HDR) having a first luminance dynamic range characterized by a first peak brightness (PB_HDR), characterized in that the luminance processor comprises: a gain calculation unit (514) arranged to calculate a multiplication factor (gL) being a function of the input luminance and a luminance mapping function (FLM); a maximum calculation unit (601) arranged to calculate a strength value (V) which is the maximal one of the three red, green and blue color components of the color of the pixel of the input image, wherein those components are either linear red, green and blue color components or a power of those linear red, green and blue color components; an overflow calculator (602) arranged to calculate an overflow measure (T) indicating how close to the upper gamut boundary the output luminance is; a gain factor modification unit (603) arranged to determine an alternative gain factor (F1(gL)) in case the overflow measure is larger than a threshold (G), and arranged to keep the original gain factor otherwise, and arranged to output one of those as a final gain factor (gF); and a multiplier (530) to multiply the input color (R′G′B′_nrm) by the final gain factor (gF) to obtain an output color (R′G′B′_HDR) having the output luminance.

A method for fingerprint enrollment, a terminal, and a non-transitory computer readable storage medium are provided. The method includes the following. An enrolled fingerprint image is acquired. The enrolled fingerprint image is compared with a preset fingerprint template. Fingerprint ID of the preset fingerprint template is determined as fingerprint ID of the enrolled fingerprint image when the enrolled fingerprint image matches the preset fingerprint template. New fingerprint ID is generated as the fingerprint ID of the enrolled fingerprint image when the enrolled fingerprint image fails to match the preset fingerprint template.

A display device and an operating method thereof are provided. The display device may include: a display; a camera; a memory configured to store one or more instructions; and a processor configured to execute the instructions to obtain an image captured by the camera, transform the image based on visual condition information of a user, the visual condition information including information about a type of visual impairment of the user, and display the transformed image on the display.

Technology for generating camera viewfinder displays for camera people video recording/broadcasting live events such as sporting events, where the viewfinder displays include overlays that include: (i) priority values for objects shown on and/or off the live event view shown in viewfinder display; (ii) identifications of objects that are outside the viewfinder display; and/or (iii) direction to the locations of objects that are outside the viewfinder display. In response to these indications in the overlay, the cameraperson may move the camera to better capture a high priority object and/or capture an object that was outside the viewfinder display.