利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

22 条记录 (耗时 0.026 秒)

    Methods and systems for person detection in a video feed
    2.
    发明授权
    Methods and systems for person detection in a video feed 有权

    公开(公告)号：US11587320B2

    公开(公告)日：2023-02-21

    申请号：US16877115

    申请日：2020-05-18

    申请人： GOOGLE LLC

    发明人： Rizwan Ahmed Chaudhry ,  Navneet Dalal ,  Jonathan Z. Ben-Meshulam ,  George Alban Heitz, III

    IPC分类号： G06V20/40 ,  G06V20/52 ,  G06K9/62 ,  H04N7/18 ,  G06T7/246 ,  G06V10/40 ,  G06V40/10

    摘要： A computing system obtains a video feed. For a frame of the video feed, the computing system analyzes the frame to determine whether the frame includes a potential instance of an event. In accordance with a determination that the frame includes the potential instance of an event, the computing system determines for the event an event category from a plurality of predefined event categories. It stores an indication of the event category. It determines whether the event category matches a predefined notification filter definition. In accordance with a determination that the event category matches the predefined notification filter definition, the computing system issues an alert notification to a user client device. In accordance with a determination that the event category does not match the predefined notification filter definition, the computing system refrains from issuing the alert notification.

    Systems and methods of person recognition in video streams
    4.
    发明授权
    Systems and methods of person recognition in video streams 有权

    公开(公告)号：US10410086B2

    公开(公告)日：2019-09-10

    申请号：US15676848

    申请日：2017-08-14

    申请人： GOOGLE LLC

    发明人： Akshay R. Bapat ,  George Alban Heitz, III ,  Rizwan Ahmed Chaudhry ,  Navneet Dalal ,  James Edward Stewart ,  Jennifer Bush ,  Joe Delone Venters ,  Kara Gates ,  Timothy Butler ,  Yohannes Kifle ,  Anton Bastov

    IPC分类号： G06K9/00 ,  G06K9/62 ,  H04N5/232

    摘要： The various implementations described herein include systems and methods for recognizing persons in video streams. In one aspect, a method includes: (1) obtaining a live video stream; (2) detecting person(s) in the stream; and (3) determining, from analysis of the live video stream, personally identifiable information of the detected person(s); (4) determining, based on the personally identifiable information, that the first person is not known to the computing system; (5) in accordance with the determination that the first person is not known: (a) storing the personally identifiable information; and (b) requesting a user to classify the first person; and (6) in accordance with (i) a determination that a predetermined amount of time has elapsed since the request was transmitted and a response was not received, or (ii) a determination that a response was received classifying the first person as a stranger, deleting the stored personally identifiable information.

    Methods and systems for person detection in a video feed
    5.
    发明授权
    Methods and systems for person detection in a video feed 有权

    公开(公告)号：US10380429B2

    公开(公告)日：2019-08-13

    申请号：US15207459

    申请日：2016-07-11

    申请人： GOOGLE LLC

    发明人： Rizwan Ahmed Chaudhry ,  Navneet Dalal ,  Jonathan Z. Ben-Meshulam ,  George Alban Heitz, III

    IPC分类号： G06K9/00 ,  G06T7/246 ,  H04N7/18 ,  G06K9/62 ,  G06K9/46

    摘要： The various embodiments described herein include methods, devices, and systems for providing event alerts. In one aspect, a method includes: (1) obtaining a video feed, the video feed comprising a plurality of images; and, (2) for each image, analyzing the image to determine whether the image includes a person, the analyzing including: (a) determining that the image includes a potential instance of a person by analyzing the image at a first resolution; (b) in accordance with the determination that the image includes the potential instance, denoting a region around the potential instance; (c) determining whether the region includes an instance of the person by analyzing the region at a second resolution, greater than the first resolution; and (d) in accordance with a determination that the region includes the instance of the person, determining that the image includes the person.

    Methods and Systems for Presenting Image Data for Detected Regions of Interest
    6.
    发明申请
    Methods and Systems for Presenting Image Data for Detected Regions of Interest 有权

    公开(公告)号：US20210216787A1

    公开(公告)日：2021-07-15

    申请号：US17216345

    申请日：2021-03-29

    申请人： Google LLC

    发明人： Joost van Hoof ,  Navneet Dalal ,  James Edward Stewart ,  Ting Yu ,  Maxime Veron ,  George Alban Heitz, III

    IPC分类号： G06K9/00 ,  G08B13/196

    摘要： A method includes obtaining from an image sensor of a video camera a primary real-time video stream comprising images of a field of view of the video camera; identifying from the primary video stream one or more regions of interest in the field of view of the video camera; while obtaining the primary video stream, creating a first video sub-stream comprising a first plurality of images for a first one of the one or more identified regions of interest, wherein: images of the first plurality of images include image data for portions of the field of the video camera that include the first identified region of interest, and the images of the first plurality of images have fields of view that are smaller than the field of view of the video camera; and providing the first video sub-stream for display at a client device.