Timeline-video relationship processing for alert events

Patent metadata

Field	Value
Publication number	US-12033389-B2
Application number	US-202217649285-A
Country	US
Kind code	B2
Filing date	Jan 28, 2022
Priority date	Oct 26, 2016
Publication date	Jul 9, 2024
Grant date	Jul 9, 2024

Abstract

A method at a server system includes: receiving a video stream from a remote video camera, wherein the video stream comprises a plurality of video frames; selecting a plurality of non-contiguous frames from the video stream, the plurality of non-contiguous frames being associated with a predetermined time interval; encoding the plurality of non-contiguous frames as a compressed video segment associated with the time interval; receiving a request from an application running on a client device to review video from the remote video camera for the time interval; and in response to the request, transmitting the video segment to the client device for viewing in the application.

First claim

What is claimed is:

1. A method, comprising:
receiving a video stream from a remote video camera, the video stream comprises a plurality of video frames;
processing, without user input, the video stream to identify one or more events;
in accordance with the processing, identifying one or more events in the video stream;
identifying a first time interval that includes at least a portion of the identified one or more events and a second time interval that does not include a portion of the identified one or more events;
selecting, without user input, a first portion and a second portion of the plurality of video frames from the video stream, the first portion of the plurality of video frames being associated with the first time interval and having a first predefined segment duration and the second portion of the plurality of video frames being associated with the second time interval and having a second predefined segment duration;
encoding, without user input, the first portion of the plurality of video frames as a first compressed video segment and the second portion of the plurality of video frames as a second compressed video segment; and
transmitting, to a client device for decoding and displaying in an application, the first compressed video segment and the second compressed video segment.

2. The method of claim 1 , wherein the plurality of video frames are evenly spaced in time.

3. The method of claim 1 , wherein the plurality of video frames are variably spaced in time, with first video frames in proximity to an identified event being spaced more closely than second video frames not in proximity to an identified event.

4. The method of claim 1 , wherein the first predefined segment duration is equal to the second predefined segment duration.

5. The method of claim 1 , wherein:
the first portion of the plurality of video frames comprises a first number of video frames;
the second portion of the plurality of video frames comprises a second number of video frames; and
the second number of video frames is less than the first number of video frames.

6. The method of claim 1 , wherein:
the first portion of the plurality of video frames comprises a plurality of contiguous frames; and
the second portion of the plurality of video frames comprises a plurality of non-contiguous frames.

7. The method of claim 1 , further comprising receiving event information from one or more of:
the remote video camera; and
one or more smart devices, wherein identifying one or more events comprises identifying one or more events based on the received event information.

8. A computer system, comprising:
one or more processors; and
memory storing one or more programs to be executed by the one or more processors, the one or more programs comprising instructions for:
receiving a video stream from a remote video camera, the video stream comprises a plurality of video frames;
processing, without user input, the video stream to identify one or more events;
in accordance with the processing, identifying one or more events in the video stream;
identifying a first time interval that includes at least a portion of the identified one or more events and a second time interval that does not include a portion of the identified one or more events;
selecting, without user input, a first portion and a second portion of the plurality of video frames from the video stream, the first portion of the plurality of video frames being associated with a the first time interval and having a first predefined segment duration and the second portion of the plurality of video frames being associated with the second time interval and having a second predefined segment duration;
encoding, without user input, the first portion of the plurality of video frames as a first compressed video segment and the second portion of the plurality of video frames as a second compressed video segment; and
transmitting, to a client device for decoding and displaying in the application, the first compressed video segment and the second compressed video segment.

9. The computer system of claim 8 , wherein a difference between the first time interval and the second time interval is any positive value.

10. The computer system of claim 8 , wherein encoding the first portion of the plurality of video frames as a first compressed video segment includes more frames than the second portion of the plurality of video frames as a second compressed video segment.

11. The computer system of claim 8 , wherein the plurality of video frames are evenly spaced in time.

12. The computer system of claim 8 , wherein the plurality of video frames are variably spaced in time, with video frames in proximity to an identified event being spaced more closely than video frames not in proximity to an identified event.

13. The computer system of claim 8 , further comprising instructions for, prior to the encoding, receiving, from the remote video camera, event information generated by the remote video camera processing the video stream.

14. The computer system of claim 8 , further comprising instructions for, prior to the encoding, receiving event information from one or more smart devices.

15. A non-transitory computer readable storage medium storing instructions, which, when executed by a computer system with one or more processors, cause the computer system to perform operations comprising:
receiving a video stream from a remote video camera, the video stream comprises a plurality of video frames;
processing, without user input, the video stream to identify one or more events;
in accordance with the processing, identifying one or more events in the video stream;
identifying a first time interval that includes at least a portion of the identified one or more events and a second time interval that does not include a portion of the identified one or more events;
selecting, without user input, a first portion and a second portion of the plurality of video frames from the video stream, the first portion of the plurality of video frames being associated with the first time interval and having a first predefined segment duration and the second portion of the plurality of video frames being associated with the second time interval and having a second predefined segment duration;
encoding, without user input, the first portion of the plurality of video frames as a first compressed video segment and the second portion of the plurality of video frames as a second compressed video segment; and
transmitting, to a client device for decoding and displaying in the application, the first compressed video segment and the second compressed video segment.

16. The computer readable storage medium of claim 15 , further comprising instructions, which, when executed by the computer system, cause the computer system to perform operations comprising: prior to the encoding, receiving, from the remote video camera, event information generated by the remote video camera processing the video stream.

17. The computer readable storage medium of claim 15 , further comprising instructions, which, when executed by the computer system, cause the computer system to perform operations comprising: prior to the encoding, receiving event information from one or more smart devices.

18. The computer readable storage medium of claim 15 , wherein transmitting the stored first compressed video segment or the stored second compressed video segment to the client device comprises transmitting:
a plurality of frames of an immediately preceding video segment; and
a pl

Assignees

• Google Llc

Inventors

• Burns Christopher Charles
• Heitz Iii George Alban
• Stewart James Edward
• Hill Cameron
• Yang Seungho
• Venters Joe Delone
• Finlayson William Alex
• Hinz Carsten
• Psiaki Timothy Samuel
• Klee Nathan Scott
• Nelson Gregory Rourk
• Avery Kevin James
• Neal Lawrence W
• Davidsson Martin

Classifications

• G06V20/44

  Event detection · CPC title

• G06V20/41

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title

• H04N7/185 Primary

  from a mobile camera, e.g. for remote control · CPC title

• G06V20/52 Primary

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title