中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

148 records (took 0.025 seconds)

    Classifying time series image data
    32.
    发明授权
    Classifying time series image data 有权

    公开(公告)号：US11017296B2

    公开(公告)日：2021-05-25

    申请号：US16108698

    申请日：2018-08-22

    Applicant: Ford Global Technologies, LLC

    Inventor： Gaurav Kumar Singh ,  Pavithra Madhavan ,  Bruno Jales Costa ,  Gintaras Vincent Puskorius ,  Dimitar Petrov Filev

    IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G06T7/246

    Abstract: The present invention extends to methods, systems, and computer program products for classifying time series image data. Aspects of the invention include encoding motion information from video frames in an eccentricity map. An eccentricity map is essentially a static image that aggregates apparent motion of objects, surfaces, and edges, from a plurality of video frames. In general, eccentricity reflects how different a data point is from the past readings of the same set of variables. Neural networks can be trained to detect and classify actions in videos from eccentricity maps. Eccentricity maps can be provided to a neural network as input. Output from the neural network can indicate if detected motion in a video is or is not classified as an action, such as, for example, a hand gesture.

    Classifying Time Series Image Data
    33.
    发明申请
    Classifying Time Series Image Data 审中-公开

    公开(公告)号：US20200065663A1

    公开(公告)日：2020-02-27

    申请号：US16108698

    申请日：2018-08-22

    Applicant: Ford Global Technologies, LLC

    Inventor： Gaurav Kumar Singh ,  Pavithra Madhavan ,  Bruno Jales Costa ,  Gintaras Vincent Puskorius ,  Dimitar Petrov Filev

    IPC: G06N3/08 ,  G06T7/246 ,  G06K9/00 ,  G06N3/04

    Abstract: The present invention extends to methods, systems, and computer program products for classifying time series image data. Aspects of the invention include encoding motion information from video frames in an eccentricity map. An eccentricity map is essentially a static image that aggregates apparent motion of objects, surfaces, and edges, from a plurality of video frames. In general, eccentricity reflects how different a data point is from the past readings of the same set of variables. Neural networks can be trained to detect and classify actions in videos from eccentricity maps. Eccentricity maps can be provided to a neural network as input. Output from the neural network can indicate if detected motion in a video is or is not classified as an action, such as, for example, a hand gesture.

    Autonomous vehicle operation based on interactive model predictive control
    34.
    发明授权
    Autonomous vehicle operation based on interactive model predictive control 有权

    公开(公告)号：US10239529B2

    公开(公告)日：2019-03-26

    申请号：US15057233

    申请日：2016-03-01

    Applicant: Ford Global Technologies, LLC

    Inventor： Dimitar Petrov Filev ,  Jianbo Lu ,  Davor D. Hrovat

    IPC: B60W10/04 ,  B60W10/20 ,  B60W30/18 ,  B60W10/18 ,  G05D1/00 ,  B60W50/00 ,  B60W10/184 ,  B60W40/04 ,  G08G1/0967

    Abstract: A system includes a computing device programmed to receive a set of goals for a vehicle and identify a travel area for the vehicle for a time period. The computing device receives data indicating predictability of driving conditions of the travel area and determines that the predictability is sufficient to control the vehicle according to model predictive control. Controlling the vehicle includes determining instructions to control actuators related to the steering, propulsion and braking of the vehicle to minimize a cost function. The instructions are implemented for a first time slot. The time period is updated to remove the first time slot at the beginning and include an additional time slot at the end of the predetermined time period. The computing device determines an updated control solution, and implements the updated control solution for a second time slot.

    Adaptive vehicle control
    35.
    发明授权
    Adaptive vehicle control 有权

    公开(公告)号：US10235818B2

    公开(公告)日：2019-03-19

    申请号：US15154166

    申请日：2016-05-13

    Applicant: Ford Global Technologies, LLC

    Inventor： Jing Wang ,  Yan Wang ,  Dimitar Petrov Filev ,  John Ottavio Michelini

    IPC: G06F19/00 ,  G07C5/08 ,  B60W30/188

    Abstract: A controller includes a processor programmed to determine, for a vehicle, a first control input based on input data and first reference parameters. The processor is further programmed to operate the vehicle according to the first control input. Based on operating data of the vehicle for an operating condition, the processor determines a second control input for the vehicle. Operating the vehicle according to the second control input reduces a cost of operating the vehicle relative to operating the vehicle according to the first control input. The processor is further programmed to determine, based on the second control input, second reference parameters. The controller generates a third control input based on the second reference parameters and the input data. A cost of operating the vehicle according to the third control input is reduced relative to the cost of operating the vehicle based on the first control input.

Patent Agency Ranking