Abstract: This disclosure relates to an apparatus for object detection. The apparatus comprises a video camera, an object detector, and a controller. The video camera may be configured to generate a video stream of frames. The object detector may be configured to accept the video stream as input data and to perform object detection. The controller may be coupled to the video camera and the object detector. The controller may be configured to manage object detection in order to satisfy a performance metric and/or operate within an operational constraint.

Abstract: Methods and apparatuses for accurately determining a model, which is to be the basis of transfer learning, among a plurality of source models, are provided. According to an embodiment, an apparatus for determining a base model to be used for transfer learning to a target domain is provided. The apparatus comprises a memory which comprises one or more instructions and a processor which executes the instructions to construct a neural network model for measuring suitability of a plurality of pre-trained source models, measure the suitability of each of the source models by inputting data of the target domain to the neural network model, and determine the base model to be used for the transfer learning among the source models based on the suitability.

Abstract: A method may include transmitting an open contention-based grant to optical network units (ONUs) and receiving, from at least one of the ONUs, a response to the open contention-based grant. The method may also include determining whether a collision has occurred in response to the open contention-based grant. The method may further include provisioning grants to ONUs in response to determine that a collision has occurred.

Abstract: An electronic device is provided, the electronic device having a keyboard including a biometric input device. The biometric input device may be a biometric key or button. A cap of a biometric key or button may include a textured ceramic cover, such as a textured sapphire cover. The cap may further include a rear decorative coating and a front antireflective coating disposed on or over the textured ceramic cover. The cap may have one or more visual and or tactile properties which resemble those of an adjacent key of the keyboard.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting locations of utility assets. One of the methods includes receiving an input image of an area in a first geographical region; generating, from the input image and using a generative adversarial network, a corresponding reference image; and generating, by an object detection model and from the reference image, an output that identifies respective locations of one or more utility assets with reference to the input image.

Abstract: An artificial intelligence (AI) decoding apparatus obtains image data corresponding to a first image, which is AI-downscaled from an original image by an AI encoding apparatus by using a first deep neural network (DNN); reconstructs a second image corresponding to the first image, based on the image data; and obtain a third image, which is AI-upscaled from the second image, convolution is performed based on the second image and second parameters of a filter kernel included in a second DNN, wherein each of the second parameters is an integer value, and the second parameters are determined as values associated with first parameters of a filter kernel included in the first DNN. Embodiments use memory-efficient values with respect to filter kernels. Parameters used to obtain the memory-efficient integer values may be obtained via joint training between the first DNN and the second DNN.

Abstract: A system and method include generation of modified imaging data and modified acquisition parameters of a training example based on the target imaging data and target acquisition parameters of each of a plurality of target examples, and generation, for each training example, of an initial reconstructed image based on the modified imaging data and modified acquisition parameters of the training example. A first network stage of a multi-stage network is trained based on the modified imaging data, modified acquisition parameters and initial reconstructed image of each training example, a first output image is generated for each training example by inputting the modified imaging data, modified acquisition parameters and initial reconstructed image of the training example to the trained first network stage, and a second network stage of the multi-stage network is trained based on the modified imaging data, modified acquisition parameters and first output image of each training example.

Abstract: An image display device configured to obtain device identification information corresponding to a peripheral device connected to the image display device and control a wireless communicator to transmit search data corresponding to the peripheral device to a control device of the image display device based on the device identification information, and to determine pairing data and control code information corresponding to the peripheral device, based on the device identification information, upon receiving response data from the control device, and transmit the pairing data and the control code information to the control device through the wireless communicator.

Abstract: A passive optical network includes a central office providing subscriber signals; a drop terminal; and a wave division multiplexer. A fiber distribution hub may split or separate out dedicated optical signals from subscriber optical signals between the central office and the drop terminal. The wave division multiplexer separates dedicated optical signals pertaining to a specific dedicated subscriber from other optical signals on the line received at the wave division multiplexer. The wave division multiplexer may be part of a cable or part of an intermediate service terminal.

Abstract: An optical receiver can implement a transimpedance amplifier (TIA) to process received light using a closed loop optical pre-amplification. The optical receiver can use an average input value of the TIA to control an semiconductor optical amplifier (SOA) or pre-amplification as received average signal varies. The optical receiver can include a gain controller for the TIA that can measure the TIA swing to adjust the gain of the SOA to pre-amplify received light in a closed loop control configuration.

Abstract: The implementations of the subject matter described herein relate to an octree-based convolutional neural network. In some implementations, there is provided a computer-implemented method for processing a three-dimensional shape. The method comprises obtaining an octree for representing the three-dimensional shape. Nodes of the octree include empty nodes and non-empty nodes. The empty nodes exclude the three-dimensional shape and are leaf nodes of the octree, and the non-empty nodes include at least a part of the three-dimensional shape. The method further comprises for nodes in the octree with a depth associated with a convolutional layer of a convolutional neural network, performing a convolutional operation of the convolutional layer to obtain an output of the convolutional layer.

Abstract: A baseband processing unit includes a baseband processor configured to receive a plurality of component carriers of a radio access technology wireless service, and a delta-sigma digitization interface configured to digitize at least one carrier signal of the plurality of component carriers into a digitized bit stream, for transport over a transport medium, by (i) oversampling the at least one carrier signal, (ii) quantizing the oversampled carrier signal into the digitized bit stream using two or fewer quantization bits.

Abstract: Disclosed are devices, systems and methods for processing an image. In one aspect a method includes receiving an image from a sensor array including an x-y array of pixels, each pixel in the x-y array of pixels having a value selected from one of three primary colors, based on a corresponding x-y value in a mask pattern. The method may further include generating a preprocessed image by performing preprocessing on the image. The method may further include performing perception on the preprocessed image to determine one or more outlines of physical objects.

Abstract: An electronic apparatus may include a memory that stores first information regarding a plurality of first artificial intelligence models trained to perform image processing differently from each other and second information regarding a second artificial intelligence model trained to identify a type of an image by predicting a processing result of the image by each of the plurality of first artificial intelligence models. The electronic apparatus may further include a processor configured to identify a type of an input image by inputting the input image to the second artificial intelligence model stored in the memory, and process the input image by inputting the input image to one of the plurality of first intelligence models stored in the memory based on the identified type.

Abstract: A system for creating synthetic data for testing an autonomous system, comprising at least one hardware processor adapted to execute a code for: using a machine learning model to compute a plurality of depth maps based on a plurality of real signals captured simultaneously from a common physical scene, each of the plurality of real signals are captured by one of a plurality of sensors, each of the plurality of computed depth maps qualifies one of the plurality of real signals; applying a point of view transformation to the plurality of real signals and the plurality of depth maps, to produce synthetic data simulating a possible signal captured from the common physical scene by a target sensor in an identified position relative to the plurality of sensors; and providing the synthetic data to at least one testing engine to test an autonomous system comprising the target sensor.

Abstract: Disclosed herein is a learning method of a neural network model for flame determination. The learning method of a neural network includes generating a learning image including a fake image generated by combining a real fire image and an arbitrary flame image with a background image; inputting the learning image to a first neural network model and outputting a determination result for whether a flame is present; and updating a weight in a layer extracting features of the learning image from the first neural network model using the determination result. According to the present invention, data of various fire situations may be secured, a performance of the neural network model that determines an occurrence of the fire through the secured data may be increased, and a quality of data for learning may be increased to allow the neural network model itself to predict various situations of fires.

Abstract: Techniques regarding multivariate time series data analysis are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a time series analysis component that generates a machine learning model that discovers a dependency between multivariate time series data using an attention mechanism controlled by an uncertainty measure.

Abstract: Enhanced methods and systems for the semantic segmentation of images are described. A refined segmentation mask for a specified object visually depicted in a source image is generated based on a coarse and/or raw segmentation mask. The refined segmentation mask is generated via a refinement process applied to the coarse segmentation mask. The refinement process correct at least a portion of both type I and type II errors, as well as refine boundaries of the specified object, associated with the coarse segmentation mask. Thus, the refined segmentation mask provides a more accurate segmentation of the object than the coarse segmentation mask. A segmentation refinement model is employed to generate the refined segmentation mask based on the coarse segmentation mask. That is, the segmentation model is employed to refine the coarse segmentation mask to generate more accurate segmentations of the object. The refinement process is an iterative refinement process carried out via a trained neural network.

Abstract: An object tracking method and apparatus are provided. The object tracking method includes detecting a target object in a first-type input image that is based on light in a first wavelength band, tracking the target object in the first-type input image based on detection information of the target object, measuring a reliability of the first-type input image by comparing the first-type image to an image in a database, comparing the reliability of the first-type input image to a threshold, and tracking the target object in a second-type input image that is based on light in a second wavelength band.

Abstract: An optical modulator of an optical transceiver can be calibrated using intermediate frequency (IF) signals to generate accurate crossing point values (e.g., DC bias). A photodiode can measure output from the optical modulator at intermediate and high-speed frequencies to generate crossing point values that avoid crossing point errors. A target crossing point can be selected at any value (e.g., 40%, 50%) and bias values can be generated from IF signals and then stored in a lookup date for setting the modulator bias during operation.