中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.019 seconds)

    Learning ordinal representations for deep reinforcement learning based object localization
    3.
    发明授权
    Learning ordinal representations for deep reinforcement learning based object localization 有权

    公开(公告)号：US12205357B2

    公开(公告)日：2025-01-21

    申请号：US17715901

    申请日：2022-04-07

    Applicant: NEC Laboratories America, Inc.

    Inventor： Shaobo Han ,  Renqiang Min ,  Tingfeng Li

    IPC: G06V10/778 ,  G06V10/82 ,  G06V30/19

    Abstract: A reinforcement learning based approach to the problem of query object localization, where an agent is trained to localize objects of interest specified by a small exemplary set. We learn a transferable reward signal formulated using the exemplary set by ordinal metric learning. It enables test-time policy adaptation to new environments where the reward signals are not readily available, and thus outperforms fine-tuning approaches that are limited to annotated images. In addition, the transferable reward allows repurposing of the trained agent for new tasks, such as annotation refinement, or selective localization from multiple common objects across a set of images. Experiments on corrupted MNIST dataset and CU-Birds dataset demonstrate the effectiveness of our approach.

    Fiber sensing using supervisory path of submarine cables
    4.
    发明授权
    Fiber sensing using supervisory path of submarine cables 有权

    公开(公告)号：US12078528B2

    公开(公告)日：2024-09-03

    申请号：US17869763

    申请日：2022-07-20

    Applicant: NEC Laboratories America, Inc.

    Inventor： Ming-Fang Huang ,  Shaobo Han ,  Yuheng Chen ,  Milad Salemi ,  Ting Wang

    IPC: G01H9/00 ,  G01D5/353

    CPC classification number: G01H9/004 ,  G01D5/35361

    Abstract: Systems, and methods for automatically identifying an underground optical fiber cable length from DFOS systems in real time and pair it with GPS coordinates that advantageously eliminate the need for in-field inspection/work by service personnel to make such real-time distance/location determinations. As such, inefficient, error-prone and labor-intensive prior art methods are rendered obsolete. Operationally, our method disclosure involves driving vehicles including GPS to generate traffic patterns and automatically mapping traffic trajectory signals from a deployed buried fiber optic cable to locate geographic location(s) of the buried fiber optic cable. Traffic patterns are automatically recognized; slack in the fiber optic cable is accounted for; location of traffic lights and other traffic control devices/structures may be determined; and turns in the fiber optic cable may likewise be determined.

    Context encoder-based fiber sensing anomaly detection
    7.
    发明授权
    Context encoder-based fiber sensing anomaly detection 有权

    公开(公告)号：US11733089B2

    公开(公告)日：2023-08-22

    申请号：US17556939

    申请日：2021-12-20

    Applicant: NEC Laboratories America, Inc.

    Inventor： Shaobo Han ,  Ming-Fang Huang ,  Eric Cosatto

    IPC: G01H9/00 ,  H04B10/071

    CPC classification number: G01H9/004 ,  H04B10/071

    Abstract: Aspects of the present disclosure describe an unsupervised context encoder-based fiber sensing method that detects anomalous vibrations proximate to a sensor fiber that is part of a distributed fiber optic sensing system (DFOS) such that damage to the sensor fiber by activities producing and anomalous vibrations are preventable. Advantageously, our method requires only normal data streams and a machine learning based operation is utilized to analyze the sensing data and report abnormal events related to construction or other fiber-threatening activities in real-time. Our machine learning algorithm is based on waterfall image inpainting by context encoder and is self-trained in an end-to-end manner and extended every time the DFOS sensor fiber is optically connected to a new route. Accordingly, our inventive method and system it is much easier to deploy as compared to supervised methods of the prior art.

    CONDITIONAL ACOUSTIC LIBRARY GENERATION FOR DISTRIBUTED FIBER OPTIC SENSOR
    9.
    发明申请
    CONDITIONAL ACOUSTIC LIBRARY GENERATION FOR DISTRIBUTED FIBER OPTIC SENSOR 有权

    公开(公告)号：US20250148294A1

    公开(公告)日：2025-05-08

    申请号：US18922807

    申请日：2024-10-22

    Applicant: NEC Laboratories America, Inc.

    Inventor： Philip Ji ,  Shaobo Han ,  Ting Wang

    IPC: G06N3/096 ,  G01H9/00

    Abstract: Systems and methods include calibrating physical parameters of acoustic data using a deterministic model related to hardware configurations that generated the acoustic data to provide an intermediate layer of data. The intermediate layer of data is then calibrated using environmental factors related to the acoustic data by employing machine learning to provide a multichannel data output. A loss is optimized between the multichannel data output and multichannel distributed-optic fiber sensing (DFOS) data to train a hybrid transfer model to translate between DFOS data and acoustic data.

    SYNTHETIC DATA FOR FIBER SENSING TASKS WITH CONTROLLABLE GENERATION AND DIFFERENTIABLE INFERENCE
    10.
    发明申请
    SYNTHETIC DATA FOR FIBER SENSING TASKS WITH CONTROLLABLE GENERATION AND DIFFERENTIABLE INFERENCE 有权

    公开(公告)号：US20250148281A1

    公开(公告)日：2025-05-08

    申请号：US18909467

    申请日：2024-10-08

    Applicant: NEC Laboratories America, Inc.

    Inventor： Shaobo Han ,  Tingfeng Li ,  Renqiang Min

    IPC: G06N3/08

    Abstract: Systems and methods include collecting real-world distributed-optic fiber sensing (DFOS) sensing data from a target environment as a reference dataset. A synthetic sketch dataset is constructed as a parameterized computer program. A synthetic waterfall is generated from a deep neural network as an image translator from the sketch waterfall with nonlinear distortions and background noises added. Parameters are optimized for generating the synthetic waterfall under a loss function where the loss function encodes a generalization performance on the real-world dataset and encodes granularities from a sensing process and uncontrollable factors.

Patent Agency Ranking