Video analytics with burst-like transmission of video data

• US 9,143,739 B2
• Filed: 05/06/2011
• Issued: 09/22/2015
• Est. Priority Date: 05/07/2010
• Status: Expired due to Fees

• Current Assignee: iWatchLife Inc.
• Original Assignee: iWatchLife Inc.
• Inventors: Murphy, William A., Phillips, Jason
• Primary Examiner(s): Senfi, Behrooz
• Assistant Examiner(s): VAZQUEZ COLON, MARIA E
• Application Number:
  US13/102,540
• Publication Number:
  US 20110273563A1
• Time in Patent Office: 1,600 Days
• Field of Search: 348/143
• US Class Current: 1/1
• CPC Class Codes: H04L 12/6418 Hybrid transport
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 5/77 between a recording apparatus and a television camera
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources
• CPC Class Codes: H04N 9/8042 involving data reduction

Abstract

A method for providing video data for video analytics processing includes capturing a plurality of individual frames of video data, using a video source that is disposed at an acquisition end. A plurality of data-frame-groups is formed, each data-frame-group being associated with a different time period of a plurality of consecutive and non-overlapping time periods. A data-frame-group that is associated with a specific time period comprises individual frames of video data that are captured during that specific time period. Additionally, each data-frame-group comprises relatively fewer individual frames of video data than are captured during the specific time period associated therewith. The plurality of data-frame-groups is transmitted from the acquisition end to a remotely located server via an IP network. In particular, the transmission of successive data-frame-groups is separated one from the other by an interval of time.

Claims

1. A method comprising:

capturing video data using a video source disposed at an acquisition end, the video data comprising a plurality of individual frames of video data that are captured during a first period of time, the individual frames of video data being captured consecutively at a known frame rate;

automatically forming a first data-frame-group comprising at least two non-consecutively captured individual frames of video data selected from the plurality of individual frames of video data, the individual frames of the at least two non-consecutively captured individual frames of video data captured at substantially regular time intervals during the first period of time, the first data-frame-group comprising non-consecutive frames including both the at least two non-consecutively captured individual frames of video data, without all intermediate frames of video data therebetween;

transmitting the first data-frame-group from the acquisition end to a remotely located server via an IP network;

automatically forming a second data-frame-group comprising at least two other non-consecutively captured individual frames of video data selected from the plurality of individual frames of video data, the individual frames of the at least two other non-consecutively captured individual frames of video data captured at substantially regular time intervals during the first period of time, the second data-frame-group comprising non-consecutive frames including both the at least two other non-consecutively captured individual frames of video data, without all intermediate frames of video data therebetween, and the second data-frame-group and the first data-frame-group in combination comprising fewer individual frames of video data than the plurality of individual frames of video data; and

,

transmitting the second data-frame-group from the acquisition end to the remotely located server via the IP network,

wherein the second data-frame-group is transmitted at a time that is separated from a time of transmission of the first data-frame-group by an interval of time that is longer than a time interval between capturing a last frame of the first data-frame-group and a first frame of the second data-frame-group, and

wherein the first data-frame group and the second data-frame group are both formed absent performing video analytics processing of the plurality of individual frames of video data that are captured during the first period of time.

2. The method according to claim 1, comprising receiving the first data-frame-group at the server and performing video analytics processing on the video data of the first data-frame-group, wherein the video analytics processing is for detecting an occurrence of an actionable event during the first period of time.

3. The method according to claim 2, comprising in response to detecting an actionable event, transmitting to the acquisition end via the IP network a signal for requesting transmission of captured video data at the known frame rate.

4. The method according to claim 2, comprising storing at the acquisition end the plurality of individual frames of video data that are captured during the first period of time.

5. The method according to claim 4, comprising in response to detecting an actionable event, transmitting to the acquisition end via the IP network as signal for requesting stored video data that was captured prior to a time of transmission of the second data-frame-group.

6. The method according to any one of claims 1 to 5, wherein each of the first data-frame-group and the second data-frame-group is limited to a predetermined maximum data size.

7. The method according to any one of claims 1 to 5, wherein the first data-frame-group is transmitted from the acquisition end to the remotely located server via the IP network during a second period of time that is subsequent to and not overlapping with the first period of time.

8. The method according to claim 1, wherein the interval of time is predetermined, such that successive data-frame-groups are transmitted to the server via, the IP network at approximately uniform time intervals.

9. The method according to claim 1, wherein the interval of time depends upon a maximum permitted size of the second data-frame-group and upon the sizes of the individual frames of the at least two other non-consecutively captured individual frames of video data.

10. The method according to claim 8, wherein the first data-frame-group and the second data-frame-group each comprise a same number of individual frames of video data.

11. The method according to claim 8 or 9, wherein the first data-frame-group and the second data-frame-group comprise a different number of individual frames of video data.

12. A method comprising:

capturing a plurality of individual frames of video data using a video source disposed at an acquisition end, the individual frames of video data being captured consecutively at a known frame rate;

automatically forming a plurality of data-frame-groups, each data-frame-group being associated with a different time period of a plurality of consecutive and non-overlapping time periods, such that a data-frame-group that is associated with as specific time period comprises at least two non-consecutively captured individual frames of video data that are captured during that specific time period and comprising non-consecutive frames including both the at least two non-consecutive captured individual frames of video data, without all intermediate frames of video data therebetween and such that each data-frame-group comprises fewer individual frames of video data than are captured during the specific time period associated therewith; and

,

transmitting, the plurality of data-frame-groups from the acquisition end to as remotely located server via an IP network, the transmission of successive data-frame-groups being separated temporally by an interval of time greater than an interval of time between capturing or a last frame included within a first data-frame-group and a first frame or a temporally adjacent subsequent data-frame-group,

wherein the data-frame-groups of the plurality of data-frame groups are formed absent performing video analytics processing of the plurality of individual frames of video data.

13. The method according to claim 12, wherein each data-frame-group of the plurality of data-frame-groups comprises a same number of individual frames of video data.

14. The method according to claim 12 or 13, wherein the interval of time is predetermined, such that successive data-frame-groups are transmitted to the server via the IP network at approximately uniform time intervals.

15. The method according to claim 12, wherein some of the data-frame-groups comprise a different number of individual frames of video data than other data-frame-groups of the plurality of data-frame-groups.

16. The method according to claim 12 or 15, wherein the interval of time depends upon a maximum permitted size of the temporally adjacent subsequent data-frame-group and upon the sizes of the individual, frames of video data that are captured during the specific time period that is associated with the temporally adjacent subsequent data-frame-group.

17. The method according to claim 12, comprising receiving each data-frame-group of the plurality of data frame groups at the server and performing video analytics processing on the video data of each data-frame-group, wherein the video analytics processing is for detecting an occurrence of an actionable event.

18. The method according to claim 17, comprising in response to detecting an actionable event, transmitting to the acquisition end via the IP network a signal for requesting transmission of captured video data at the known frame rate.

19. The method according to claim 12, comprising storing at the acquisition end the plurality of individual frames of video data.