Abstract: Systems, devices, media and methods are presented for generating biometric image data. In one example, a system accesses a set of images stored on a mobile computing device. The system identifies one or more faces depicted in the set of images and generates a set of face images from the set of images. The system determines a set of positions of a set of facial features depicted within the set of face images and generates a set of biometric reference maps based on the set of positions. The system transmits the set of face images to a reference server and stores the set of biometric reference maps on the mobile computing device.

Abstract: Motion detection is performed using layouts of different resolutions. A plurality of layouts at different resolutions are generated using an image. Sets of bounding boxes for the different layouts are generated based on areas indicative of motion for the respective layout. The different sets of bounding boxes are combined and motion of one or more objects represented in the image is detected based on combined set of bounding boxes.

Abstract: Methods and systems for utilizing a mobile computing device (e.g., such as a mobile phone) for use in controlling a model vehicle are described. Consistent with some embodiments, a mobile computing device provides various user controls for generating signals that are communicated to a radio transmitter device coupled with the mobile computing device, and ultimately broadcast to a receiver residing at a model vehicle. With some embodiments, the mobile computing device may be integrated with a controller housing which provides separate user controls, such that a combination of user controls present on the mobile computing device and the controller housing can be used to control a model vehicle.

Abstract: Methods and systems for implementing an object identification system equipped to reduce the number of service calls for remote object identification lookups are disclosed. The object identification management server works to reduce the number of object identification requests, which overall improves the process of quickly and accurately providing object identifications when needed and without unnecessarily wasting computing resources. The object identification server can subsequently manage the number of identification requests by setting a tunable threshold, which allows a system to operate more efficiently and allocate computing resources accordingly.

Abstract: The present disclosure generally relates to implementing an operational safety mode that manages the output of notifications at an electronic device when a user of the device is operating a vehicle.

Abstract: A trailer assist system for a vehicle includes a camera disposed at a rear portion of a vehicle and having a field of view exterior and at least rearward of the vehicle, the field of view encompassing at least a portion of a trailer coupler of a trailer stationary a distance from the vehicle. The camera captures image data that is representative of at least the trailer coupler of the trailer. An ECU includes an image processor operable to process image data captured by the camera. The ECU, responsive to image processing at the ECU of image data captured by the camera, determines a location of the trailer coupler using a detector model, which is based on an ensemble regression tree algorithm.

Abstract: Methods and systems are disclosed for boosting deep neural networks for deep learning. In one example, in a deep neural network including a first shallow network and a second shallow network, a first training sample is processed by the first shallow network using equal weights. A loss for the first shallow network is determined based on the processed training sample using equal weights. Weights for the second shallow network are adjusted based on the determined loss for the first shallow network. A second training sample is processed by the second shallow network using the adjusted weights. In another example, in a deep neural network including a first weak network and a second weak network, a first subset of training samples is processed by the first weak network using initialized weights. A classification error for the first weak network on the first subset of training samples is determined.

Abstract: A method for measuring the sensitivity of an image classifier, which assigns an input image to one or multiple classes of a predefined classification, to modifications of the input image. The method includes: the input image is mapped by at least one predefined operator onto an intermediate image, which has a lesser information content and/or a poorer signal-to-noise ratio in comparison to the input image; at least one generator is provided, which is trained to generate realistic images, which image classifier assigns to a specific class of the predefined classification; the generator is used to generate a variation of the input image from the intermediate image.

Abstract: In various examples, object detections of a machine learning model are leveraged to automatically generate new ground truth data for images captured at different perspectives. The machine learning model may generate a prediction of a detected object at the different perspective, and an object tracking algorithm may be used to track the object through other images in a sequence of images where the machine learning model may not have detected the object. New ground truth data may be generated as a result of the object tracking algorithms outputs, and the new ground truth data may be used to retrain or update the machine learning model, train a different machine learning model, or increase the robustness of a ground truth data set that may be used for training machine learning models from various perspectives.

Abstract: An object recognition system 80 includes: a recognition device 30 that recognizes an object in an image; and a server 40 that generates a learning model. The recognition device 30 includes: a first object recognition unit 310 that determines a type of the object in the image using the learning model; and an image transmission unit 320 that transmits a type-indeterminable image, which is an image in which the type has not been determined, to the server 40 when an object included in the type-indeterminable image is an object detected as a three-dimensional object. The server 40 includes: a learning device 410 that generates the learning model based on training data in which a teacher label is assigned to the type-indeterminable image; and a learning model transmission unit 420 that transmits the generated learning model to the recognition device 30. The first object recognition unit 310 determines the type of the object in the image using the transmitted learning model.

Abstract: A computer implemented method for detecting whether a seat belt is used in a vehicle comprises the following steps carried out by computer hardware components: acquiring an image of an interior of the vehicle; determining a plurality of sub-images based on the image; detecting, for at least one of the sub-images, whether a portion of the seat belt is present in the respective sub-image; and determining whether the seat belt is used based on the detecting.

Abstract: A communications hub providing a repository of vehicle crash information communicated by a mobile communications device and of vehicle crash data records provided by crash event servicers, in a crash detection, response and reporting system that determines a possible crash event by periodically evaluating (a) changes in a motion signal and (b) crash sound indicators of one or more of (i) motor vehicle glass breakage, (ii) metal folding, (iii) contact thud, and (iv) tires screeching, and upon a failure to respond within a predetermined period to a notice of possible crash event, communicating an identifier and crash incident information to a dispatch center as first notice of loss for dispatching a response servicer and maintaining the repository to facilitate resolution of the claims arising from the vehicle crash event.

Abstract: Systems, devices, and methods disclosed herein represent existing photo or video content within computer generated reality (CGR) environments. In some implementations, a representation of an existing photo or video is positioned within a CGR environment based on the position of the camera of the existing photo/video at the time the existing photo or video was captured. For example, a user experiencing CGR while walking along a hiking trail may see a floating representation of a photo that the user took on his or her last trip on that hiking trail. The representation may be positioned and oriented in the same position and orientation that the camera was positioned and oriented in when the photo was first captured, e.g., 5 feet above the ground, three feet north of the hiking trail welcome sign. The representation may be a version of the image itself or provide information about the image.

Abstract: Systems for image evaluation and dynamic cropping are provided. In some examples, a system, may receive an instrument or image of an instrument. Identifying information may be extracted from the instrument or image of the instrument. Based on the extracted identifying information, a check/check image profile may be retrieved. In some examples, expected size and/or shape data may be extracted from the check/check image profile. The extracted expected size and/or shape data may be compared to size and/or shape data from the received instrument or image of the instrument to identify any anomalies (e.g., to determine whether the expected size and/or shape data matches the size and/or shape data of the received instrument or image of the instrument. If the expected size and/or shape data does not match size and/or shape data from the received instrument or image of the instrument, the instrument or image of the instrument may be programmatically modified and a modified image of the instrument may be generated.

Abstract: Techniques are provided for giving access to restricted content on a first device from a second device through a wireless network. In one embodiment, the first device transmits an authorization request signal to the second device or to a server in the wireless network. The second device, having received the authorization request, prompts an authorized user to give authorization to the first device by inputting an authentication key such as a password or gesture on the second device. Upon verification of the authentication key, an authorization signal may be wirelessly transmitted to the first device, permitting access to the restricted content or functions on the first device. In some embodiments, the second device may be alerted to an authorization request and may select a request for authorization from a selectable queue of requests.

Abstract: A depth calculation processor includes: an input port, configured to receive image data from an image sensor; a demultiplexer, connected to the input port, and configured to demultiplex the image data from the input port and output first image data into a first line and second image data into a second line; a grayscale image engine, configured to process the first image data from the first line to generate processed first image data; a depth image engine, configured to receive the second image data from the second line, and calculate depth image data based on the second image data; a multiplexer, configured to output the processed first image data from the grayscale image engine and the depth image data from the depth image engine; and an output port, configured to output the processed first image data and the depth image data from the multiplexer.

Abstract: A vehicle can use an image sensor to both detect objects and determine depth data associated with the environment the vehicle is traversing. The vehicle can capture image data and lidar data using the various sensors. The image data can be provided to a machine-learned model trained to output depth data of an environment. Such models may be trained, for example, by using lidar data and/or three-dimensional map data associated with a region in which training images and/or lidar data were captured as ground truth data. The autonomous vehicle can further process the depth data and generate additional data including localization data, three-dimensional bounding boxes, and relative depth data and use the depth data and/or the additional data to autonomously traverse the environment, provide calibration/validation for vehicle sensors, and the like.

Abstract: Systems and methods are disclosed for connection and disconnection of a shared audio endpoint. In one aspect, a method includes detecting a charging event of a user mobile device being electrically coupled to a charger, and in response to detecting the charging event, broadcasting a beacon comprising a name of a shared audio endpoint. The shared audio endpoint accepts a connection request to connect the user mobile device to the shared audio endpoint based on the beacon.

Abstract: Provided are methods for prediction error scenario mining for machine learning methods, which can include determining a prediction error indicative of a difference between a planned decision of an autonomous vehicle and an ideal decision of the autonomous vehicle. The prediction error is associated with an error-prone scenario for which a machine learning model of an autonomous vehicle is to make planned movements. The method includes searching a scenario database for the error-prone scenario based on the prediction error. The scenario database includes a plurality of datasets representative of data received from an autonomous vehicle sensor system in which the plurality of datasets is marked with at least one attribute of the set of attributes. The method further includes obtaining the error-prone scenario from the scenario database for inputting into the machine learning model for training the machine learning model. Systems and computer program products are also provided.

Abstract: The present disclosure relates to a communication method and system for converging a 5th-Generation (5G) communication system for supporting higher data rates beyond a 4th-Generation (4G) system with a technology for Internet of Things (IoT). A method for determining transmitting resources in vehicle to vehicle/pedestrian/infrastructure/network (V2X) communication is provided.