利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

10 条记录 (耗时 0.016 秒)

    Tuning layers of a modular neural network
    1.
    发明授权
    Tuning layers of a modular neural network 有权

    公开(公告)号：US11352014B1

    公开(公告)日：2022-06-07

    申请号：US17454790

    申请日：2021-11-12

    申请人： Samsara Inc.

    发明人： Sharan Srinivasan ,  Brian Tuan ,  John Bicket ,  Jing Wang ,  Muhammad Ali Akhtar ,  Abner Ayala Acevedo ,  Bruce Kellerman ,  Vincent Shieh

    IPC分类号： B60W40/09 ,  G06N3/08 ,  G06N3/04 ,  G06V40/20

    摘要： A vehicle device may execute one or more neural networks (and/or other artificial intelligence), based on input from one or more of the cameras and/or other sensors, to intelligently detect safety events in real-time. The one or more neural networks may be an ensemble neural network that includes neural networks for detecting a head and hand of a user, neural networks for detecting hand actions of the user, neural networks for detecting the head pose of the user, neural networks for predicting an occurrence of an event, and neural networks for predicting a start time and end time of the event. Further, the neural networks can be segmented into a modular neural network based on metadata. The segmentation of the neural network can define a thin layer of the modular neural network to enable independent tuning of the thin layer of the modular neural network.

    Detection of camera with impaired view
    2.
    发明授权
    Detection of camera with impaired view 有权

    公开(公告)号：US12112548B1

    公开(公告)日：2024-10-08

    申请号：US18618182

    申请日：2024-03-27

    申请人： Samsara Inc.

    发明人： Shaurye Agarwal ,  Akshay Raj Dhamija ,  Howard Yu ,  Margaret Irene Finch ,  Jing Wang ,  Rohit Annigeri ,  Sharan Srinivasan ,  Yan Wang ,  Nathan Hurst

    IPC分类号： G06V20/56 ,  G06T3/60 ,  G06V10/44 ,  G06V10/764

    CPC分类号： G06V20/56 ,  G06T3/60 ,  G06V10/44 ,  G06V10/764

    摘要： Methods, systems, and programs are presented for detecting impaired views in monitoring cameras. One method includes training a rotation classifier with unsupervised learning utilizing a first set of images. The rotation classifier is configured to receive an input image and generate a rotation feature embedding for the input image. In addition, the method includes training an impairment classifier with supervised learning utilizing a second set of images, impairment labels for each of the second set of images, and the rotation feature embedding, generated by the rotation classifier, for each of the second set of images. The method further includes accessing a vehicle image captured by a camera on a vehicle, and providing the vehicle image to the impairment classifier as input, and the impairment classifier outputs a camera impairment from a set of camera impairment categories. Further, the vehicle image and the camera impairment are presented on a user interface.

    Ensemble neural network state machine for detecting distractions
    10.
    发明授权
    Ensemble neural network state machine for detecting distractions 有权

    公开(公告)号：US11386325B1

    公开(公告)日：2022-07-12

    申请号：US17454799

    申请日：2021-11-12

    申请人： Samsara Inc.

    发明人： Sharan Srinivasan ,  Brian Tuan ,  John Bicket ,  Jing Wang ,  Muhammad Ali Akhtar ,  Abner Ayala Acevedo ,  Bruce Kellerman ,  Vincent Shieh

    IPC分类号： G06N3/08 ,  G06N7/00 ,  B60W40/09 ,  B60W50/14 ,  G06N20/20

    摘要： A vehicle device may execute one or more neural networks (and/or other artificial intelligence), based on input from one or more of the cameras and/or other sensors, to intelligently detect safety events in real-time. The one or more neural networks may be an ensemble neural network that includes neural networks for detecting a head and hand of a user, neural networks for detecting hand actions of the user, neural networks for detecting the head pose of the user, neural networks for predicting an occurrence of an event, and neural networks for predicting a start time and end time of the event. Further, the neural networks can be segmented into a modular neural network based on metadata. The segmentation of the neural network can define a thin layer of the modular neural network to enable independent tuning of the thin layer of the modular neural network.