Method for and apparatus for detecting events

Patent metadata

Field	Value
Publication number	US-11055856-B2
Application number	US-201715851340-A
Country	US
Kind code	B2
Filing date	Dec 21, 2017
Priority date	Dec 21, 2016
Publication date	Jul 6, 2021
Grant date	Jul 6, 2021

Abstract

A method for detecting events comprises repeatedly registering a value indicating an amount of data generated by an encoder, which is encoding video from a scene by means of temporal compression, determining if a particular event has occurred in the scene represented by the encoded video by comparing characteristics of the registered values with predetermined characteristics, and generating an event signal in response to an event occurrence being determined.

First claim

What is claimed is:

1. Method for detecting events, comprising:
measuring a data rate of an encoded video stream of a scene that has been encoded by temporal compression over a plurality of consecutive time intervals to generate a plurality of values corresponding to each of the consecutive time intervals;
removing all of the plurality of values that correspond to image frames that are not temporally encoded to generate a dataset; and
detecting events representing objects traveling towards or away from a camera used for capturing the scene by comparing a derivative of portions on both sides of a peak of a representation of the data rate against time of the dataset.

2. The method according to claim 1 , further including storing the dataset in a database, wherein the act of detecting events is performed on the dataset stored in the database.

3. The method according to claim 1 , further including transferring the dataset over a network to a client, wherein the act of detecting events is performed by the client.

4. The method according to claim 1 , further comprising indicating a velocity of an object triggering a detection of an event by analyzing steepness of the portions of the representation of the data rate against time of the dataset.

5. The method according to claim 1 , further comprising identifying a size of an object triggering a detection of an event by analyzing a height of the peak.

6. The method according to claim 1 , further comprising incrementing a counter each time the occurrence of an event has been detected.

7. The method according to claim 1 , further comprising incrementing a counter related to a particular event each time the occurrence of that particular event has been identified.

8. The method according to claim 1 , wherein the removing all of the plurality of values that correspond to image frames that are not temporally encoded comprises removing all values from the first dataset that are above a maximum threshold value.

9. A method for detecting events, the method comprising:
measuring a data rate of an encoded video stream of a scene that has been encoded by temporal compression over a plurality of consecutive time intervals to generate a plurality of values corresponding to each of the consecutive time intervals;
removing all of the plurality of values that correspond to image frames that are not temporally encoded to generate a dataset;
detecting an event by analyzing a representation of the data rate against time of the dataset; and
indicating a velocity of an object triggering a detection of an event by analyzing steepness of a portion of the representation of the data rate against time of the dataset.

10. The method according to claim 9 , further including storing the dataset in a database, wherein the act of detecting events is performed on the dataset stored in the database.

11. The method according to claim 9 , further including transferring the dataset over a network to a client, wherein the act detecting events is performed by the client.

12. The method according to claim 9 , further comprising incrementing a counter each time the occurrence of an event has been detected.

13. The method according to claim 9 , further comprising incrementing a counter related to a particular event each time the occurrence of that particular event has been identified.

14. The method according to claim 9 , wherein the removing all of the plurality of values that correspond to image frames that are not temporally encoded comprises removing all values from the first dataset that are above a maximum threshold value.

15. A method for detecting events comprising:
measuring a data rate of an encoded video stream of a scene that has been encoded by temporal compression over a plurality of consecutive time intervals to generate a plurality of values corresponding to each of the consecutive time intervals;
removing from all of the plurality of values that correspond to image frames that are not temporally encoded to generate a dataset;
detecting an event by analyzing a peak of a representation of the data rate against time of the dataset; and
identifying a size of an object triggering a detection of an event by analyzing a height of the peak.

16. The method according to claim 15 , further including storing the dataset in a database, wherein the act of detecting events is performed on the dataset stored in the database.

17. The method according to claim 15 , further including transferring the dataset over a network to a client, wherein the act detecting events is performed by the client.

18. The method according to claim 15 , further comprising incrementing a counter each time the occurrence of an event has been detected.

19. The method according to claim 15 , further comprising incrementing a counter related to a particular event each time the occurrence of that particular event has been identified.

20. The method according to claim 15 , wherein the removing all of the plurality of values that correspond to image frames that are not temporally encoded comprises removing all values from the first dataset that are above a maximum threshold value.

Assignees

• Axis Ab

Inventors

• Edpalm Viktor
• Andersson Erik

Classifications

• G06V20/44

  Event detection · CPC title

• H04N19/146 Primary

  Data rate or code amount at the encoder output · CPC title

• H04N5/147 Primary

  Scene change detection · CPC title

• H04N21/23418 Primary

  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 title

• G06V20/53

  Recognition of crowd images, e.g. recognition of crowd congestion · CPC title