中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

169 records (took 0.024 seconds)

    IDENTIFYING REGIONS OF INTEREST IN AN IMAGING FIELD OF VIEW
    1.
    发明申请
    IDENTIFYING REGIONS OF INTEREST IN AN IMAGING FIELD OF VIEW 审中-公开

    公开(公告)号：WO2023091444A1

    公开(公告)日：2023-05-25

    申请号：PCT/US2022/050037

    申请日：2022-11-16

    Applicant: SIMPLISAFE, INC.

    Inventor： JACOB, Jacquilene

    IPC: G06T7/20 ,  G06V20/52 ,  G06V20/40 ,  G06V10/22 ,  G06V10/25 ,  G06V10/26 ,  G06V20/70

    Abstract: The techniques described herein relate to computerized methods, systems and non-transitory computer-readable media for determining a plurality of regions of interest from an image of a scene for motion detection. The methods can include generating the regions of interest using image segmentation techniques and receiving user selection to designate one or more regions as motion detection zones. The methods can also automatically recommend motion detection zones. The methods can include subsequently capturing one or more images of a scene and performing motion detection in the one or more images of the scene using the designated motion detection zones.

    SPORTS NEURAL NETWORK CODEC
    3.
    发明申请
    SPORTS NEURAL NETWORK CODEC 审中-公开

    公开(公告)号：WO2023077008A1

    公开(公告)日：2023-05-04

    申请号：PCT/US2022/078794

    申请日：2022-10-27

    Applicant: STATS LLC

    Inventor： COLAMATTEO, Valerio ,  EVI-PARKER, Christopher ,  PADAGADI, Sateesh ,  LUCEY, Patrick Joseph

    IPC: G06T7/246 ,  G06V20/40 ,  G06T7/292 ,  G06N3/04

    Abstract: A computing system receives a broadcast video stream of a game. A codec module of the computing system extracts image level features from the broadcast video stream. The codec module includes an object detection portion configured to detect players in the broadcast video stream and a subnet portion attached to the object detection portion. The subnet portion is configured to identify foreground information of the detected players. The codec module provides the image level features to a plurality of task specific modules for analysis. The plurality of task specific modules generates a plurality of outputs based on the image level features.

    基于时空增强网络的视频动作识别方法
    5.
    发明申请
    基于时空增强网络的视频动作识别方法 审中-公开

    公开(公告)号：WO2023065759A1

    公开(公告)日：2023-04-27

    申请号：PCT/CN2022/108524

    申请日：2022-07-28

    Applicant: 苏州大学

    Inventor： 黄鹤 ,  余佳诺

    IPC: G06V20/40

    Abstract: 一种基于时空增强网络的视频动作识别方法，包括：S1.将视频划分为T个等长的时间段并从每个时间段中随机采样一帧，获得具有T帧图像的输入序列；S2.将S1获取到的视频帧图像序列进行预处理；S3.以S2得到的张量作为输入并将其输入到时空增强网络模型中，经过模型处理后得到提取的时空特征；S4.用softmax激活并归一化S3得到的时空特征并沿着时间维度对归一化后的时空特征求平均，最后通过变形得到的就是各个视频中行为的分类分数，再取最高分所属分类作为分类类别即可得到所求分类结果。该方法的有益效果：通过在空间网络中嵌入时空增强模块，基于深度学习的视频行为识别系统可以得到较高的分类准确率。

    PROCESSING VIDEO CONTENT USING GATED TRANSFORMER NEURAL NETWORKS
    8.
    发明申请
    PROCESSING VIDEO CONTENT USING GATED TRANSFORMER NEURAL NETWORKS 审中-公开

    公开(公告)号：WO2023049726A1

    公开(公告)日：2023-03-30

    申请号：PCT/US2022/076752

    申请日：2022-09-21

    Applicant: QUALCOMM INCORPORATED

    Inventor： LI, Yawei ,  MOONS, Bert ,  BLANKEVOORT, Tijmen Pieter Frederik ,  HABIBIAN, Amirhossein ,  EHTESHAMI BEJNORDI, Babak

    IPC: G06V10/20 ,  G06V20/40 ,  G06V10/82

    Abstract: Certain aspects of the present disclosure provide techniques and apparatus for processing a video stream using a machine learning model. An example method generally includes generating a first group of tokens from a first frame of the video stream and a second group of tokens from a second frame of the video stream. A first set of tokens associated with features to be reused from the first frame and a second set of tokens associated with features to be computed from the second frame are identified based on a comparison of tokens from the first group of tokens to corresponding tokens in the second group of tokens. A feature output is generated for portions of the second frame corresponding to the second set of tokens. Features associated with the first set of tokens are combined with the generated feature output into a representation of the second frame.

    CONTEXT-CONTROLLED VIDEO QUALITY CAMERA SYSTEM
    10.
    发明申请
    CONTEXT-CONTROLLED VIDEO QUALITY CAMERA SYSTEM 审中-公开

    公开(公告)号：WO2023003928A1

    公开(公告)日：2023-01-26

    申请号：PCT/US2022/037668

    申请日：2022-07-20

    Applicant: SHAH, Nishant

    Inventor： SHAH, Nishant

    IPC: G06V20/40 ,  G06F16/783 ,  G06V20/52

    Abstract: A context-controlled video quality camera system running a software application to perform video quality settings actions in response to triggering conditions suggesting a recording context in which particular values of one or more video quality settings are preferred. Triggering conditions include a geolocation of a camera device, a present time, and/or sensed ambient conditions. Video quality settings actions include either automatically adjusting settings to the particular values or prompting a user to select whether to adjust the settings. Rules having triggering conditions and corresponding video quality settings actions can include default rules of the software application. The rules can be updated on the user's own initiative or in response to identified triggering patterns of user activity, either automatically or as selected by a user in response to automatic pro

Patent Agency Ranking