Smart optical cable positioning/location using optical fiber sensing

    公开(公告)号:US11366231B2

    公开(公告)日:2022-06-21

    申请号:US16660699

    申请日:2019-10-22

    Abstract: Aspects of the present disclosure describe systems, methods and structures for determining any location on a deployed fiber cable from an optical time domain reflectometry (OTDR) curve using a movable mechanical vibration source to stimulate tiny vibration of fiber in deployed fiber cable along the cable route and a fiber sensing system at a central office to detect the vibration(s). Latitude and longitude of the location(s) of the vibration source is measured with a GPS device and a dynamic-OTDR distance is measured at central office (CO) simultaneously. The collected GPS location data and corresponding dynamic-OTDR distance data are paired and saved into a database. This saved data may be processed to graphically overlie a map thereby providing exact cable location on the map thereby providing carriers/service providers the ability to improve fiber fault location on a deployed fiber cable much faster and more accurately than presently possible using methods available in the art.

    Unmanned aerial vehicle network
    84.
    发明授权

    公开(公告)号:US11356172B2

    公开(公告)日:2022-06-07

    申请号:US16816605

    申请日:2020-03-12

    Abstract: Systems and methods implementing a multi-unmanned aerial vehicle (UAV) wireless communication network are provided. The system includes application UAVs that wirelessly provide applications. The system includes relay UAVs that connect the application UAVs to a ground station. The ground station connects to a wireless backhaul network. Processor devices determine mobility for the application UAVs based on application-specific objectives. The processor devices also determine mobility for the relay UAVs based on forming and maintaining the wireless backhaul network.

    Object recognizer emulation
    85.
    发明授权

    公开(公告)号:US11354935B2

    公开(公告)日:2022-06-07

    申请号:US16810061

    申请日:2020-03-05

    Abstract: A computer-implemented method for emulating an object recognizer includes receiving testing image data, and emulating, by employing a first object recognizer, a second object recognizer. Emulating the second object recognizer includes using the first object recognizer to perform object recognition on a testing object from the testing image data to generate data, the data including a feature representation for the testing object, and classifying the testing object based on the feature representation and a machine learning model configured to predict whether the testing object would be recognized by a second object recognizer. The method further includes triggering an action to be performed based on the classification.

    FACE CLUSTERING WITH IMAGE UNCERTAINTY

    公开(公告)号:US20220156484A1

    公开(公告)日:2022-05-19

    申请号:US17526492

    申请日:2021-11-15

    Abstract: Methods and systems for face clustering include determining a quality score for each of a set of input images. A first subset of the input images is clustered, having respective quality scores that exceed a predetermined threshold, to form an initial set of clusters. A second subset of the input images is clustered, having respective quality scores below the predetermined threshold. An action is performed responsive to the clustered images after the second subset is added to the initial set of clusters.

    DOMAIN GENERALIZED MARGIN VIA META-LEARNING FOR DEEP FACE RECOGNITION

    公开(公告)号:US20220147767A1

    公开(公告)日:2022-05-12

    申请号:US17521252

    申请日:2021-11-08

    Abstract: A method for training a model for face recognition is provided. The method forward trains a training batch of samples to form a face recognition model w(t), and calculates sample weights for the batch. The method obtains a training batch gradient with respect to model weights thereof and updates, using the gradient, the model w(t) to a face recognition model what(t). The method forwards a validation batch of samples to the face recognition model what(t). The method obtains a validation batch gradient, and updates, using the validation batch gradient and what(t), a sample-level importance weight of samples in the training batch to obtain an updated sample-level importance weight. The method obtains a training batch upgraded gradient based on the updated sample-level importance weight of the training batch samples, and updates, using the upgraded gradient, the model w(t) to a trained model w(t+1) corresponding to a next iteration.

    DIVIDE-AND-CONQUER FOR LANE-AWARE DIVERSE TRAJECTORY PREDICTION

    公开(公告)号:US20220144256A1

    公开(公告)日:2022-05-12

    申请号:US17521139

    申请日:2021-11-08

    Abstract: A method for driving path prediction is provided. The method concatenates past trajectory features and lane centerline features in a channel dimension at an agent's respective location in a top view map to obtain concatenated features thereat. The method obtains convolutional features derived from the top view map, the concatenated features, and a single representation of the training scene the vehicle and agent interactions. The method extracts hypercolumn descriptor vectors which include the convolutional features from the agent's respective location in the top view map. The method obtains primary and auxiliary trajectory predictions from the hypercolumn descriptor vectors. The method generates a respective score for each of the primary and auxiliary trajectory predictions. The method trains a vehicle trajectory prediction neural network using a reconstruction loss, a regularization loss objective, and an IOC loss objective responsive to the respective score for each of the primary and auxiliary trajectory predictions.

Patent Agency Ranking