利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

6 条记录 (耗时 0.013 秒)

    ENHANCED MACHINE LEARNING MODEL FOR JOINT DETECTION AND MULTI PERSON POSE ESTIMATION
    1.
    发明申请
    ENHANCED MACHINE LEARNING MODEL FOR JOINT DETECTION AND MULTI PERSON POSE ESTIMATION 有权

    公开(公告)号：US20230137337A1

    公开(公告)日：2023-05-04

    申请号：US17851651

    申请日：2022-06-28

    申请人： TEXAS INSTRUMENTS INCORPORATED

    发明人： Debapriya MAJI ,  Soyeb NAGORI ,  Manu MATHEW ,  Deepak Kumar PODDAR

    IPC分类号： G06V10/25 ,  G06V10/44 ,  G06V10/74

    摘要： A technique for key-point detection, including receiving, by a machine learning model, an input image, generating a set of image features for the input image, determining, by the machine learning model, based on the set of image features, a bounding box for an object detected in the input image, the bounding box described by bounding box information, identifying, by the machine learning model, based on the set of image features and a center point of the bounding box, a plurality of key-points associated with the object, filtering the plurality of key-points based on a confidence score associated with each key-point of the plurality of key-points, and outputting coordinates of the plurality of key-points, confidence scores associated with the plurality of key-points, and the bounding box information.

    MACHINE LEARNING MODEL WITH WATERMARKED WEIGHTS
    3.
    发明申请
    MACHINE LEARNING MODEL WITH WATERMARKED WEIGHTS 有权

    公开(公告)号：US20220012312A1

    公开(公告)日：2022-01-13

    申请号：US17487517

    申请日：2021-09-28

    申请人： TEXAS INSTRUMENTS INCORPORATED

    发明人： Deepak Kumar PODDAR ,  Mihir MODY ,  Veeramanikandan RAJU ,  Jason A.T. JONES

    IPC分类号： G06F21/16 ,  G06N3/04 ,  G06N20/00 ,  G06F21/12

    摘要： In some examples, a system includes storage storing a machine learning model, wherein the machine learning model comprises a plurality of layers comprising multiple weights. The system also includes a processing unit coupled to the storage and operable to group the weights in each layer into a plurality of partitions; determine a number of least significant bits to be used for watermarking in each of the plurality of partitions; insert one or more watermark bits into the determined least significant bits for each of the plurality of partitions; and scramble one or more of the weight bits to produce watermarked and scrambled weights. The system also includes an output device to provide the watermarked and scrambled weights to another device.

    MACHINE LEARNING MODEL WITH WATERMARKED WEIGHTS
    4.
    发明申请
    MACHINE LEARNING MODEL WITH WATERMARKED WEIGHTS 审中-公开

    公开(公告)号：US20190205508A1

    公开(公告)日：2019-07-04

    申请号：US16188560

    申请日：2018-11-13

    申请人： TEXAS INSTRUMENTS INCORPORATED

    发明人： Deepak Kumar PODDAR ,  Mihir MODY ,  Veeramanikandan RAJU ,  Jason A.T. JONES

    IPC分类号： G06F21/16 ,  G06F15/18 ,  G06N3/04

    CPC分类号： G06F21/16 ,  G06N3/0472 ,  G06N20/00

    摘要： In some examples, a system includes storage storing a machine learning model, wherein the machine learning model comprises a plurality of layers comprising multiple weights. The system also includes a processing unit coupled to the storage and operable to group the weights in each layer into a plurality of partitions; determine a number of least significant bits to be used for watermarking in each of the plurality of partitions; insert one or more watermark bits into the determined least significant bits for each of the plurality of partitions; and scramble one or more of the weight bits to produce watermarked and scrambled weights. The system also includes an output device to provide the watermarked and scrambled weights to another device.

    FEATURE POINT IDENTIFICATION IN SPARSE OPTICAL FLOW BASED TRACKING IN A COMPUTER VISION SYSTEM
    5.
    发明公开
    FEATURE POINT IDENTIFICATION IN SPARSE OPTICAL FLOW BASED TRACKING IN A COMPUTER VISION SYSTEM 审中-公开

    公开(公告)号：US20240153105A1

    公开(公告)日：2024-05-09

    申请号：US18414772

    申请日：2024-01-17

    申请人： TEXAS INSTRUMENTS INCORPORATED

    发明人： Deepak Kumar PODDAR ,  Anshu JAIN ,  Desappan KUMAR ,  Pramod Kumar SWAMI

    IPC分类号： G06T7/246

    CPC分类号： G06T7/246 ,  G06T2200/28 ,  G06T2207/20016 ,  G06T2207/30241

    摘要： A method for sparse optical flow based tracking in a computer vision system is provided that includes detecting feature points in a frame captured by a monocular camera in the computer vision system to generate a plurality of detected feature points, generating a binary image indicating locations of the detected feature points with a bit value of one, wherein all other locations in the binary image have a bit value of zero, generating another binary image indicating neighborhoods of currently tracked points, wherein locations of the neighborhoods in the binary image have a bit value of zero and all other locations in the binary image have a bit value of one, and performing a binary AND of the two binary images to generate another binary image, wherein locations in the binary image having a bit value of one indicate new feature points detected in the frame.