Abstract: Systems and methods for three-dimensional imaging are disclosed. A three-dimensional imaging system may include a light source to emit a light pulse. The divergence of the light pulse may be configurable by the system. For example, the system may also include a receiving lens having a field of view and configured to receive a portion of the light pulse reflected or scattered by a scene. The system may configure the light source so that the divergence of the light pulse matches or approximates the field of view of the receiving lens.

Abstract: An image decoding device includes a prediction unit configured to generate a prediction signal included in a prediction block based on a motion vector. The prediction unit is configured to perform refinement processing of setting a search range based on a reference position specified by the motion vector, specifying a corrected reference position having the smallest predetermined cost from the search range, and correcting the motion vector based on the corrected reference position. When a block size of the prediction block is larger than a predetermined block size, the prediction unit is configured to divide the prediction block into sub-block groups and perform the refinement processing for each sub-block.

Abstract: A well log is scanned for one or more dimensions that describe one or more features of a well. Each dimension includes a plurality of values in a numerical format that represents each dimension. A missing value is detected in a first plurality of values of a first dimension of the well log. The first dimension of the well log is transformed, in response to the missing value, into a first image that visually depicts the first dimension including the first plurality of values and the missing value. Based on the first image and based on an image analysis algorithm a second image is created that visually depicts the first plurality of values and includes a found depiction visually depicting a found value in place of the missing value. The found depiction is converted, based on the second image, into a first value in the numerical format.

Abstract: Using locality sensitive hashing in federated machine learning. A server receives from clients locality sensitive hash (LSH) vectors. In one embodiment, the server groups the clients into clusters, based on the LSH vectors; the server selects a subset of the clients, by choosing at least one client from each of the clusters. In another embodiment, the server finds a subset of the clients, by minimize gradient divergence for the subset of the clients. The server receives from selected clients LSH vectors computed based on parameter vectors of updated models, and based on LSH vectors the server determines whether the updated models are sufficiently different from a model being trained; in response to determining that the updated models are sufficiently different from the model, the server requests the selected clients to send the parameter vectors to the server.

Abstract: A vehicular camera includes an imager printed circuit board and a lens having a plurality of optical elements. The lens is held in optical alignment with an imager at the imager printed circuit board via a dual cure one-part, filled adhesive that in its uncured state has an epoxy resin. The adhesive is both UV-curable and thermal-curable. A flexible electrical ribbon cable electrically connects circuitry of the imager printed circuit board with additional circuitry of the vehicular camera. Image data captured by the imager is provided to the additional circuitry of the vehicular camera via the flexible electrical ribbon cable. The additional circuitry includes at least a processor for processing image data captured by the imager and provided to the additional circuitry via the flexible electrical ribbon cable. The vehicular camera, when installed and used in a vehicle, captures image data for use by a vision system of the vehicle.

Abstract: Drone-based inventory management method and systems. One embodiment provides a drone-based inventory management system including one or more unmanned aerial vehicles (UAVs), and a central management system having an electronic processor, and a transceiver configured to communicate with the one or more UAVs. The electronic processor is configured to determine a discrepancy in inventory and select a UAV for verification. The electronic processor is also configured to determine whether weather permits UAV operation and operate the UAV in a pre-determined route when the weather permits UAV operation. The electronic processor is further configured to capture images using the UAV and determine new inventory based on captured images. The electronic processor is also configured to update inventory based on the new inventory.

Abstract: An example apparatus for tracking objects includes a controller to receive a depth map, a focus distance, and an image frame of an object to be tracked. The controller is to detect the object to be tracked in the image frame and generate an object position for the object in the image frame. The controller is to calculate a deflection angle for the object based on the depth map, the focus distance, and the object position. The controller is to further rotate an imaging sensor based on the deflection angle.

Abstract: Disclosed is an image data encoding/decoding method and apparatus. A method for decoding a 360-degree image comprises the steps of: receiving a bitstream obtained by encoding a 360-degree image; generating a prediction image by making reference to syntax information obtained from the received bitstream; combining the generated prediction image with a residual image obtained by dequantizing and inverse-transforming the bitstream, so as to obtain a decoded image; and reconstructing the decoded image into a 360-degree image according to a projection format.

Abstract: A light source unit, a light receiving unit that includes a distance image sensor in which a plurality of pixels each including a photoelectric conversion device generating electric charge corresponding to incident light and a plurality of electric charge accumulating units accumulating the electric charge and dividing and accumulating the electric charge among the electric charge accumulating units at a predetermined accumulation timing are arranged in a two-dimensional matrix pattern, a distance image processing unit that is configured to acquire a distance from a subject present in the space that is an imaging target, and a timing determining unit that is configured to determine the accumulation timing in the measurement time interval on the basis of an electric charge amount in each of the electric charge accumulating units in an inspection time interval in which the light pulse is not emitted at the accumulation timing are provided.

Abstract: Edge devices utilizing personalized machine learning and methods of operating the same are disclosed. An example edge device includes a model accessor to access a first machine learning model from a cloud service provider. A local data interface is to collect local user data. A model trainer is to train the first machine learning model to create a second machine learning model using the local user data. A local permissions data store is to store permissions indicating constraints on the local user data with respect to sharing outside of the edge device. A permissions enforcer is to apply permissions to the local user data to create a sub-set of the local user data to be shared outside of the edge device. A transmitter is to provide the sub-set of the local user data to a public data repository.

Abstract: Technologies for user-assisted machine learning includes a compute device configured to request user assistance to classify sensor data in response to a determination that a confidence score associated with the classification of the sensor data is below a threshold value and/or if the classification of the sensor data is unknown. In an illustrative embodiment, the compute device is configured to communicate with an activity monitor device, such as a smart pet collar, to determine activities of the subject (e.g., a pet) based on classification data received from the smart pet collar.

Abstract: Multipurpose systems can include networked devices configured to include microphones, motion sensors, video cameras, touchscreens, optical sensors, speakers, or other suitable devices. The networked devices can include networking capabilities that enable the networked device to communicate with target devices and other networked devices. A system of networked devices can identify a target location or a target device by analyzing audio signals received at microphones of the networked devices. For example, a plurality of networked devices can identify a particular networked device that is in closest proximity to a user by analyzing an audio intensity of an audio signal received at the plurality of networked devices. The identified networked device can serve as a master device that can control a state of target devices.

Abstract: There are provided an imaging device, a distance measurement method, a distance measurement program, and a recording medium capable of accurately measuring a distance to a subject without depending on a color of the subject.

Abstract: Implementations set forth herein relate to a camera calibration system for generating various types of calibration data by maneuvering a camera through a variety of different calibration test systems. The calibration data generated by the camera calibration system can be transmitted to the camera, which can locally store the calibration data. The calibration data can include spatial frequency response value data, which can be generated according to a spatial frequency response test that is performed by the camera calibration system. The calibration data can also include field of view values and distortion values that are generated according to a distortion test that is also performed by the camera calibration system. The camera calibration system can maneuver the camera through a variety of different calibration tests, as well as transmit any resulting calibration data to the camera for storage.

Abstract: A method for use with a computing device. The method may include receiving a data set including a plurality of univariate data points and determining a target kernel bandwidth for a kernel density estimator (KDE). Determining the target kernel bandwidth may include computing a plurality of sample KDEs and selecting the target kernel bandwidth based on the sample KDEs. The method may further include computing the KDE for the data set using the target kernel bandwidth. For one or more tail regions of the data set, the method may further include computing one or more respective tail extensions. The method may further include computing and outputting a renormalized piecewise density estimator that, in each tail region, equals a renormalization of the respective tail extension for that tail region, and, outside the one or more tail regions, equals a renormalization of the KDE.

Abstract: Technologies relating to improving performance of a computer-implemented model that acts as a multi-class classifier are described herein. A chatbot includes the computer-implemented model, and the computer-implemented model receives natural language input from end users. A subset of the natural language inputs are identified as training examples that are to be used to update the computer-implemented model, wherein the natural language inputs are identified as the training examples based upon comparisons between scores for the natural language inputs output by different classifiers of the computer-implemented model. The training examples are labeled by a developer, and the computer-implemented model is updated based upon the labeled training examples.

Abstract: An encoder is provided that comprises a partitioner and an entropy coder. The partitioner is configured to receive a current block of the frame and obtain a list of candidate geometric partitioning (GP) lines. Each of the candidate GP lines is generated based on information of one or more candidate neighbor blocks of the current block. The partitioner is further configured to determine a final GP line that partitions the current block into two segments, select a GP line from the list of GP lines to obtain a selected GP line, and generate a GP parameter for the current block. The GP parameter includes an offset information indicating an offset between the final GP line and the selected GP line. The entropy coder is configured to encode the GP parameter.

Abstract: Systems, apparatuses, and methods are described for encoding media content based on an ending delay of first media content and a startup delay of second media content. Second media content may be configured for transmission after first media content in a media content stream. The first media content may be associated with an ending delay corresponding to transmission and/or decoding of frames of the first media content. The second media content may be associated with a starting delay corresponding to transmission and/or decoding of frames of the second media content. The first media content and the second media content may be encoded using different encoding formats. Based on comparing the ending delay and starting delay to a threshold, encoding parameters may be selected, one or more frames may be removed from the first media content and/or the second media content, and/or buffers of one or more devices may be adjusted.

Abstract: A signal processing device is disclosed, which includes a plurality of channel receivers, a plurality of time code processors in one-to-one correspondence with the channel receivers, a timing generator, a signal processor and a transmitter, wherein each channel receiver is configured to parse an audio-video signal which has a data format defined by the SDI protocol and including a time code that characterizes time information. Each time code processor is configured to extract the time code from a parsed audio-video signal obtained by a corresponding channel receiver, and form first frame image data including a frame time code. The signal processor is configured to form an absolute frame output image based on multiple channels of the first frame of image data, frame time codes therein, and an internal clock signal generated by the timing generator. The transmitter is configured to transmit the absolute frame output image for display.

Abstract: The present application provides a position detecting method, device and storage medium for a vehicle ladar, where the method includes: detecting, through a ladar disposed on an autonomous vehicle, detection data of at least one wall of an interior room in which the autonomous vehicle is located, obtaining a point cloud image according to the detection data of the at least one wall, and judging, according to the point cloud image, whether an installation position of the ladar is accurate. According to the technical solution, it is possible to accurately detect whether the installation position of the ladar is accurate, provide a prerequisite for calibration of the installation position of the ladar, and improve detection accuracy of the ladar for obstacles around the autonomous vehicle.