知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.019 seconds)

    Real Time Visual Mitigation of a Live Camera Feed
    21.
    发明公开
    Real Time Visual Mitigation of a Live Camera Feed 审中-公开

    公开(公告)号：US20240005630A1

    公开(公告)日：2024-01-04

    申请号：US18344514

    申请日：2023-06-29

    Applicant: Apple Inc.

    Inventor： Mohammad Haris Baig ,  Praveen Gowda Ippadi Veerabhadre Gowda

    IPC: G06V10/75 ,  G06V10/25 ,  G06V10/54 ,  G06F3/01 ,  G06F3/14

    CPC classification number: G06V10/758 ,  G06V10/25 ,  G06V10/54 ,  G06F3/013 ,  G06F3/14

    Abstract: Mitigating triggering display conditions includes obtaining an image frame, comprising image data captured by a camera, determining, from the image data, an image statistic for at least a portion of the image frame. The technique also includes determining that the image statistic satisfies a trigger criterion, where the trigger criterion is associated with at least one predetermined display condition and, in response, modifying an image parameter for the at least a portion of the image frame. The technique also includes rendering the image frame, in accordance with the modified image parameter, where the predetermined display condition is avoided in the rendered image frame, in accordance with the rendering, and displaying the rendered image frame.

    Plane detection using semantic segmentation
    23.
    发明授权
    Plane detection using semantic segmentation 有权

    公开(公告)号：US11610397B2

    公开(公告)日：2023-03-21

    申请号：US17473469

    申请日：2021-09-13

    Applicant: Apple Inc.

    Inventor： Daniel Ulbricht ,  Angela Blechschmidt ,  Mohammad Haris Baig ,  Tanmay Batra ,  Eshan Verma ,  Amit Kumar KC

    IPC: G06V20/10 ,  G06T7/70 ,  G06V30/262 ,  G06K9/62 ,  G06T19/00

    Abstract: In one implementation, a method of generating a plane hypothesis is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels. The method includes obtaining a plurality of points of a point cloud based on the image of the scene. The method includes obtaining an object classification set based on the image of the scene. Each element of the object classification set includes a plurality of pixels respectively associated with a corresponding object in the scene. The method includes detecting a plane within the scene by identifying a subset of the plurality of points of the point cloud that correspond to a particular element of the object classification set.

    Computer vision using a prior probability distribution selected based on an image capture condition
    24.
    发明授权
    Computer vision using a prior probability distribution selected based on an image capture condition 有权

    公开(公告)号：US11468275B1

    公开(公告)日：2022-10-11

    申请号：US16744425

    申请日：2020-01-16

    Applicant: Apple Inc.

    Inventor： Angela Blechschmidt ,  Daniel Ulbricht ,  Mohammad Haris Baig

    IPC: G06K9/62 ,  G06N20/00 ,  G06V10/20 ,  G06N3/08

    Abstract: A machine learning (ML) model is trained and used to produce a probability distribution associated with a computer vision task. The ML model uses a prior probability distribution associated with a particular image capture condition determined based on sensor data. For example, given that an image was captured by an image capture device at a particular height above the floor and angle relative to the vertical world axis, a prior probability distribution for that particular image capture device condition can be used in performing a computer vision task on the image. Accordingly, the machine learning model is given the image as input as well as the prior probability distribution for the particular image capture device condition. The use of the prior probability distribution can improve the accuracy, efficiency, or effectiveness of the ML learning model for the computer vison task.

    Generating a contextual information vector for improved scene understanding
    25.
    发明授权
    Generating a contextual information vector for improved scene understanding 有权

    公开(公告)号：US11430238B1

    公开(公告)日：2022-08-30

    申请号：US16838934

    申请日：2020-04-02

    Applicant: Apple Inc.

    Inventor： Angela Blechschmidt ,  Mohammad Haris Baig ,  Daniel Ulbricht

    IPC: G06V30/262 ,  G06K9/62 ,  G06V10/40 ,  G06N3/04 ,  G06T7/60 ,  G06N3/08

    Abstract: In one implementation, a method of generating a confidence value for a result from a primary task is performed at an image processing system. The method includes obtaining, by a feature extractor portion of the neural network, a set of feature maps for an image data frame; generating a contextual information vector associated with the image data frame based on results from one or more auxiliary tasks performed on the set of feature maps by an auxiliary task sub-network portion of the neural network; performing, by a primary task sub-network portion of the neural network, a primary task on the set of feature maps for the image data frame in order to generate a primary task result; and generating a confidence value based on the contextual information vector, wherein the confidence value corresponds to a reliability metric for the primary task result.

Patent Agency Ranking