Video analytics with pre-processing at the source end

• US 9,788,017 B2
• Filed: 10/07/2010
• Issued: 10/10/2017
• Est. Priority Date: 10/07/2009
• Status: Active Grant

• Current Assignee: Hanwha Vision Company Limited (Hanwha Corporation)
• Original Assignee: iWatchLife Inc.
• Inventors: Laganiere, Robert, Murphy, William, Blais, Pascal, Phillips, Jason
• Primary Examiner(s): Werner, David N
• Application Number:
  US13/500,711
• Publication Number:
  US 20120195363A1
• Time in Patent Office: 2,560 Days
• Field of Search: None
• CPC Class Codes: G08B 17/125 by using a video camera to detect fire or smoke
• CPC Class Codes: H04L 12/6418 Hybrid transport
• CPC Class Codes: H04N 19/85 using pre-processing or post-processing specially adapted for video compression
• CPC Class Codes: H04N 21/632 using a connection between clients on a wide area network, e.g. setting up a peer-to-peer communication via Internet for retrieving video segments from the hard-disk of other client devices broadcast-related systems characterised by transmission among terminal devices H04H60/80; distributed application using peer-to-peer [P2P] networks H04L67/104
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A method for performing video analytics includes receiving at a source end video data including first video data relating to an event of interest. Using video analytics, other than a data compression process, pre-processing of the video data is performed at the source end to reduce the bandwidth requirement for transmitting the video data to below a bandwidth limit of a Wide Area Network (WAN) over which the video data is to be transmitted. The pre-processed video data is transmitted to a central server via the WAN, where other video analytics processing of the pre-processed video data is performed. Based on a result of the other video analytics processing, a signal is generated for performing a predetermined action, in response to an occurrence of the event of interest at the source end.

Claims

1. A method comprising:

receiving at a source end video data including first video data relating to an event of interest and second video data other than relating to the event of interest, the video data captured using a video camera disposed at the source end;

using video analytics to detect the first video data and the second video data within the video data;

pre-processing the video data at the source end to reduce the bandwidth requirement for transmitting the pre-processed video data to below a bandwidth limit of a Wide Area Network (WAN) over which the pre-processed video data is to be transmitted, wherein the pre-processing comprises selectively formatting the second video data differently than the first video data;

transmitting the pre-processed video data to a central server via the WAN;

performing other video analytics processing of the pre-processed video data at other than the source end; and

,

based on a result of the other video analytics processing, generating a signal for performing a predetermined action in response to an occurrence of the event of interest at the source end.

2. A method according to claim 1, wherein the other video analytics is performed using a processor of the central server.

3. A method according to claim 1, comprising transmitting the pre-processed video data from the central server to a first video analytics engine selected from a plurality of available video analytics engines.

4. A method according to claim 3 comprising transmitting from the source end to the central server pre-processing results, other than the video data itself, relating to a result of pre-processing the video data, and wherein the first video analytics engine is selected based on the pre-processing results.

5. A method according to claim 3, wherein the first video analytics engine performs the other video analytics.

6. A method according to claim 1, wherein pre-processing the video data comprises cropping a portion of the video data.

7. A method according to claim 1, wherein pre-processing the video data comprises varying a color depth of a portion of the video data.

8. A method according to claim 1, wherein pre-processing the video data comprises providing a portion of the video data containing the event of interest at a higher resolution than a portion of the video data that does not contain the event of interest.

9. A method according to claim 1, wherein pre-processing the video data comprises providing a portion of the video data containing the event of interest at a higher frame rate than a portion of the video data that does not contain the event of interest.

10. A method according to claim 1, wherein pre-processing the video data comprises compressing the video data using a data compression process, based on video analytics other than the data compression process.

11. A method according to claim 1, wherein the signal is for generating one of an alert and a control signal.

12. A method comprising:

receiving video data at a source end, the video data including video data relating to an event of interest captured using a video camera disposed at the source end;

using video analytics other than a data compression process, pre-processing the video data at the source end such that a first portion of the video data in which the event of interest is detected is formatted differently than a second portion of the video data in which the event of interest is other than detected;

transmitting the pre-processed video data from the source end to a central server via a Wide Area Network (WAN);

performing other video analytics processing of the pre-processed video data at other than the source end; and

,

based on a result of the other video analytics, generating a signal for performing a predetermined action in response to an occurrence of the event of interest at the source end,

wherein pre-processing reduces the bandwidth requirement for transmitting the second portion of the video data, such that a time-averaged bandwidth requirement of the pre-processed video data is lower than a bandwidth limit of the WAN over which the pre-processed video data is to be transmitted.

13. A method according to claim 12, wherein pre-processing comprises applying a first data compression process to the first portion of the video data and applying a second data compression process to the second portion of the video data, the first data compression process different than the second data compression process.

14. A method according to claim 13, wherein the first data compression process is a lossless data compression process and the second data compression process is a lossy data compression process.

15. A method according to claim 12, wherein pre-processing of the video data is performed for enhancing the first portion of the video data for being processed by the additional video analytics.

16. A method according to claim 12, wherein pre-processing of the video data is performed for transmitting the first portion of the video data at a higher frame rate than the second portion of the video data.

17. A method according to claim 12, wherein pre-processing of the video data is performed for transmitting the first portion of the video data at a higher resolution than the second portion of the video data.

18. A method according to claim 12, wherein the signal is for generating an alert.