中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.009 seconds)

    DATA ACQUISTION AND INPUT OF NEURAL NETWORK METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW
    1.
    发明申请
    DATA ACQUISTION AND INPUT OF NEURAL NETWORK METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW 审中-公开

    公开(公告)号：US20190080166A1

    公开(公告)日：2019-03-14

    申请号：US15703852

    申请日：2017-09-13

    Applicant: TUSIMPLE

    Inventor： WENTAO ZHU ,  YI WANG ,  YI LUO

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/52 ,  G05D1/00

    Abstract: A method of visual odometry for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, causes the computing device to perform the following steps comprising: performing data alignment; obtaining data from sensors; based on the data from the sensors, performing machine learning in a visual odometry model; generating a prediction of static optical flow; generating motion parameters; and training the visual odometry model by using at least one of the prediction of static optical flow and the motion parameters.

    TRAINING AND TESTING OF A NEURAL NETWORK SYSTEM FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW
    2.
    发明申请
    TRAINING AND TESTING OF A NEURAL NETWORK SYSTEM FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW 审中-公开

    公开(公告)号：US20190079536A1

    公开(公告)日：2019-03-14

    申请号：US15703900

    申请日：2017-09-13

    Applicant: TUSIMPLE

    Inventor： WENTAO ZHU ,  YI WANG ,  YI LUO

    IPC: G05D1/02 ,  G06T7/207 ,  G06N3/08

    Abstract: A system for visual odometry is provided. The system includes: an internet server, comprising: an I/O port, configured to transmit and receive electrical signals to and from a client device; a memory; one or more processing units; and one or more programs stored in the memory and configured for execution by the one or more processing units, the one or more programs including instructions for: in response to images in pairs, generating a prediction of static scene optical flow for each pair of the images in a visual odometry model; generating a set of motion parameters for each pair of the images in the visual odometry model; training the visual odometry model by using the prediction of static scene optical flow and the motion parameters; and predicting motion between a pair of consecutive image frames by the trained visual odometry model.

    NEURAL NETWORK ARCHITECTURE SYSTEM FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW
    3.
    发明申请
    NEURAL NETWORK ARCHITECTURE SYSTEM FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW 审中-公开

    公开(公告)号：US20190079534A1

    公开(公告)日：2019-03-14

    申请号：US15703879

    申请日：2017-09-13

    Applicant: TUSIMPLE

    Inventor： WENTAO ZHU ,  YI WANG ,  YI LUO

    IPC: G05D1/02 ,  G06K9/46 ,  G06K9/62 ,  G06T7/246 ,  G01C21/16 ,  G01C21/32 ,  G01S17/89 ,  G06N5/02 ,  G06N99/00

    Abstract: A system for visual odometry is disclosed. The system includes: an internet server, comprising: an I/O port, configured to transmit and receive electrical signals to and from a client device; a memory; one or more processing units; and one or more programs stored in the memory and configured for execution by the one or more processing units, the one or more programs including instructions for: extracting representative features from a pair input images in a first convolution neural network (CNN) in a visual odometry model; merging, in a first merge module, outputs from the first CNN; decreasing feature map size in a second CNN; generating a first flow output for each layer in a first deconvolution neural network (DNN); merging, in a second merge module, outputs from the second CNN and the first DNN; generating a second flow output for each layer in a second DNN; and reducing accumulated errors in a recurrent neural network (RNN).

    TRAINING AND TESTING OF A NEURAL NETWORK METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW
    5.
    发明申请
    TRAINING AND TESTING OF A NEURAL NETWORK METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW 审中-公开

    公开(公告)号：US20190079535A1

    公开(公告)日：2019-03-14

    申请号：US15703896

    申请日：2017-09-13

    Applicant: TUSIMPLE

    Inventor： WENTAO ZHU ,  YI WANG ,  YI LUO

    IPC: G05D1/02 ,  G06T7/207 ,  G06N3/08

    Abstract: A method of visual odometry for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs include instructions, which when executed by a computing device, causes the computing device to perform the following steps comprising: in response to images in pairs, generating a prediction of static scene optical flow for each pair of the images in a visual odometry model; generating a set of motion parameters for each pair of the images in the visual odometry model; training the visual odometry model by using the prediction of static scene optical flow and the motion parameters; and predicting motion between a pair of consecutive image frames by the trained visual odometry model.

    NEURAL NETWORK ARCHITECTURE METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW
    6.
    发明申请
    NEURAL NETWORK ARCHITECTURE METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW 审中-公开

    公开(公告)号：US20190079533A1

    公开(公告)日：2019-03-14

    申请号：US15703874

    申请日：2017-09-13

    Applicant: TUSIMPLE

    Inventor： WENTAO ZHU ,  YI WANG ,  YI LUO

    IPC: G05D1/02 ,  G01S17/89 ,  G01C21/16 ,  G06K9/00 ,  G06N5/02 ,  G06N99/00

    Abstract: A method of visual odometry for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs includes instructions, which when executed by a computing device, causes the computing device to perform the following steps comprising: extracting representative features from a pair input images in a first convolution neural network (CNN) in a visual odometry model; merging, in a first merge module, outputs from the first CNN; decreasing feature map size in a second CNN; generating a first flow output for each layer in a first deconvolution neural network (DNN); merging, in a second merge module, outputs from the second CNN and the first DNN; generating a second flow output for each layer in a second DNN; and reducing accumulated errors in a recurrent neural network (RNN).

    OUTPUT OF A NEURAL NETWORK METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW
    7.
    发明申请
    OUTPUT OF A NEURAL NETWORK METHOD FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW 审中-公开

    公开(公告)号：US20190080470A1

    公开(公告)日：2019-03-14

    申请号：US15703885

    申请日：2017-09-13

    Applicant: TUSIMPLE

    Inventor： WENTAO ZHU ,  YI WANG ,  YI LUO

    IPC: G06T7/73 ,  G05D1/02 ,  G06T7/55 ,  G06K9/32

    Abstract: A method of visual odometry for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs includes instructions, which when executed by a computing device, causes the computing device to perform the following steps comprising: performing data alignment among sensors including a LiDAR, cameras and an IMU-GPS module; collecting image data and generating point clouds; processing, in the IMU-GPS module, a pair of consecutive images in the image data to recognize pixels corresponding to a same point in the point clouds; and establishing an optical flow for visual odometry.

    DATA ACQUISTION AND INPUT OF NEURAL NETWORK SYSTEM FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW
    8.
    发明申请
    DATA ACQUISTION AND INPUT OF NEURAL NETWORK SYSTEM FOR DEEP ODOMETRY ASSISTED BY STATIC SCENE OPTICAL FLOW 审中-公开

    公开(公告)号：US20190080167A1

    公开(公告)日：2019-03-14

    申请号：US15703863

    申请日：2017-09-13

    Applicant: TUSIMPLE

    Inventor： WENTAO ZHU ,  YI WANG ,  YI LUO

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/52 ,  G05D1/00

    Abstract: A system for visual odometry is disclosed. The system includes: an internet server, comprising: an I/O port, configured to transmit and receive electrical signals to and from a client device; a memory; one or more processing units; and one or more programs stored in the memory and configured for execution by the one or more processing units, the one or more programs including instructions for: performing data alignment; obtaining data from sensors; based on the data from the sensors, performing machine learning in a visual odometry model; generating a prediction of static optical flow; generating motion parameters; and training the visual odometry model by using at least one of the prediction of static optical flow and the motion parameters.

Patent Agency Ranking