公开(公告)号：US12118036B2

公开(公告)日：2024-10-15

申请号：US17352067

申请日：2021-06-18

Applicant: Google LLC

Inventor： Yi Shen ,  Xiangrong Chen ,  Min-hsuan Tsai ,  Yun Shi ,  Tianpeng Jin ,  Zheng Sun ,  Weilong Yang ,  Jingbin Wang ,  Carolyn Au ,  James Futrell

IPC: G06F16/738 ,  G06F16/783 ,  G06F18/22 ,  G06T7/20 ,  G06T7/90 ,  G06V20/40 ,  G11B27/031

CPC classification number: G06F16/739 ,  G06F16/7837 ,  G06F16/785 ,  G06F16/786 ,  G06F18/22 ,  G06T7/20 ,  G06T7/90 ,  G06V20/47 ,  G11B27/031 ,  G06T2207/10016

Abstract: Systems and methods of automatically extracting summaries of video content are described herein. A data processing system can access, from a video database, a first video content element including a first plurality of frame. The data processing system can select an intervallic subset of the first plurality of frames of the first video content element. The data processing system can calculate, for each of a plurality of further subsets comprising a predetermined number of frames from the intervallic subset, a score for the further subset. The data processing system can identify, from the plurality of further subsets, a further subset having a highest score. The data processing system can select a portion of the first video content element comprising the frames of the further subset having the highest score. The data processing system can generate a second video content element comprising the selected portion of the first video content element.

公开(公告)号：US20240314373A1

公开(公告)日：2024-09-19

申请号：US18120947

申请日：2023-03-13

Applicant: Google LLC

Inventor： Brianne Courtney Mirecki ,  Mayank Prakash Mohta ,  James Futrell ,  Kong Man Cheung

IPC: H04N21/2365 ,  H04N21/2187 ,  H04N21/2368 ,  H04N21/439 ,  H04N21/442 ,  H04N21/4627 ,  H04N21/472 ,  H04N21/485 ,  H04N21/488

CPC classification number: H04N21/2365 ,  H04N21/2187 ,  H04N21/2368 ,  H04N21/439 ,  H04N21/44222 ,  H04N21/4627 ,  H04N21/472 ,  H04N21/4858 ,  H04N21/4884

Abstract: Methods and systems for a server-generated mosaic video stream of live-stream media items are provided herein. A plurality of source video streams is identified by a server. The plurality of source video streams are combined into a mosaic video stream, wherein each source video stream of the plurality of source video streams occupies a corresponding spatial fragment of a predefined shape within a visual rendering of the mosaic video stream, and wherein video frames of the plurality of source video streams are simultaneously present within the mosaic video stream. The mosaic video stream is transmitted to a client device for decoding and visual rendering within an output window.