Apparatus and methods for video alarm verification

• US 8,804,997 B2
• Filed: 07/16/2008
• Issued: 08/12/2014
• Est. Priority Date: 07/16/2007
• Status: Active Grant

• Current Assignee: CheckVideo, LLC (Kastle Systems International LLC)
• Original Assignee: CheckVideo, LLC (Kastle Systems International LLC)
• Inventors: Gagvani, Nikhil, Robertson, Philip Allen
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): ANSARI, TAHMINA N
• Application Number:
  US12/174,225
• Publication Number:
  US 20090022362A1
• Time in Patent Office: 2,218 Days
• US Class Current: 382/100
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06V 20/41 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 Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08B 13/19615 wherein said pattern is defined by the user
• CPC Class Codes: G08B 13/19663 Surveillance related processing done local to the camera
• CPC Class Codes: G08B 13/19667 Details realated to data compression, encryption or encoding, e.g. resolution modes for reducing data volume to lower transmission bandwidth or memory requirements
• CPC Class Codes: G08B 13/1968 Interfaces for setting up or customising the system
• CPC Class Codes: G08B 13/19684 Portable terminal, e.g. mobile phone, used for viewing video remotely
• CPC Class Codes: G08B 13/19695 Arrangements wherein non-video detectors start video recording or forwarding but do not generate an alarm themselves
• CPC Class Codes: G08B 13/19697 Arrangements wherein non-video detectors generate an alarm themselves
• CPC Class Codes: G08B 25/001 Alarm cancelling procedures or alarm forwarding decisions, e.g. based on absence of alarm confirmation
• CPC Class Codes: G08B 29/185 Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system

Abstract

A method for verification of alarms is disclosed. The method involves receiving an alarm signal trigger associated with an alarm signal, receiving video data from a premise associated with the alarm signal, rapidly analyzing the video data to test for the existence a significant event, and when a significant event exists, sending a representation of a segment of interest of the video data, the segment of interest being associated with the significant event, to a user.

Claims

1. A method for authenticating an alarm, comprising:

receiving from an alarm sensor at a monitored premise an alarm signal associated with an event at the monitored premise;

receiving video data of the monitored premise from a video source associated with the alarm sensor;

conducting video analytics on the video data to detect the event in a segment of interest of the video data;

identifying an event type associated with the event;

selecting a level of encoding for the segment of interest of the video data based at least in part on the event type being associated with a profile;

encoding the segment of interest based on the level of encoding to produce encoded video data having a bit rate different than a bit rate of the video data;

selecting a level of encoding for a portion of the video data different from the segment of interest, the level of encoding for the segment of interest being different from the level of encoding for the portion of the video data; and

sending a representation of the encoded video data to at least one recipient.

2. The method of claim 1, wherein the alarm sensor is selected from a group consisting of a motion sensor, a glass breakage sensor, a door contact sensor, a window contact sensor, an infrared sensor, a sound sensor, a pressure sensor, a tension sensor, a magnetic sensor, a temperature sensor, a humidity sensor, and a fire or smoke sensor.

3. The method of claim 1, wherein the alarm sensor is selected from a group consisting of an electronic access control system output, a security keypad, and a biometric identification system.

4. The method of claim 1, further comprising:

retrieving routing instructions from the profile in response to the encoding, the sending includes sending the representation of the encoded video data according to the routing instructions.

5. The method of claim 1, wherein the conducting video analytics includes consulting the profile to determine parameters for use in the video analytics.

18. The method of claim 1, wherein the level of encoding for the segment of interest is a first level of encoding and the encoded video data is first encoded video data, the sending includes sending the first encoded video data to a storage server to be cached, the method further comprising:

encoding the segment of interest based on a second level of encoding different from the first level of encoding, to produce second encoded video data different from the first encoded video data; and

sending a representation of the second encoded video data to the at least one recipient.

19. The method of claim 1, wherein the selecting the level of encoding for the segment of interest includes selecting the level of encoding for the segment of interest based at least in part on a device type associated with the at least one recipient.

20. The method of claim 1, wherein the representation of the encoded video data includes the encoded video data.

21. The method of claim 1, wherein the representation of the encoded video data includes a link to provide access to the encoded video data.

22. The method of claim 1, wherein the profile is a user-defined profile.

23. The method of claim 1, wherein the profile is from a plurality of profiles, each profile from the plurality of profiles includes parameters associated with an authorization level of the event based at least in part on at least one of the event type, a schedule associated with the event, a time of a day, a day of a week, a day of a month, or a time period.

24. The method of claim 1, wherein the video analytics is conducted at a video analytics module collocated with the video source.

33. The method of claim 1, wherein the sending the representation of the encoded video data, includes consulting the profile to determine at least one of the at least one recipient or a device type.

6. A system for verifying alarms, comprising:

a video analytics module configured to analyze video data received from a video source associated with a monitored premise to determine an identity of a person in the video data based at least in part on a user-defined profile, the video analytics module configured to determine an authorization level of the person based on the identity, the video analytics module configured to determine, based on the authorization level, that the person is unauthorized, the video analytics module configured to verify an alarm condition at the monitored premise in response to the person being unauthorized;

an encode module configured to receive from the video analytics module a confirmation of the alarm condition including a representation of the video data, the encode module configured to encode using a first level of encoding, based on the confirmation of the alarm condition, a first portion of the video data to produce encoded video data, the encode module configured to select a level of encoding for a second portion of the video data different from the first portion of the video data, the level of encoding for the first portion being different from the level of encoding for the second portion; and

an alert module configured to receive from the encode module a confirmation of the alarm condition, including a representation of the encoded video data, the alert module configured to send to a recipient an alert including a representation of the encoded video data regarding the alarm condition.

7. The system of claim 6, further comprising:

a profile module storing the user-defined profile including parameters associated with temporal variance of the operation of the alert module based on at least one of a time of a day, a day of a week, a day of a month, or a time period.

8. The system of claim 6, wherein the user-defined profile stores a user-defined process flow, the video analytics module is configured to perform hierarchical analysis of the video data by executing the user-defined process flow to verify the alarm condition.

9. The system of claim 6, wherein the alert module is configured to select the recipient based on a type of the alarm condition and the user-defined profile.

10. The system of claim 6, wherein the video analytics module is configured to determine a degree of video analysis to be performed on the video data based on a type of the alarm condition and the user-defined profile.

11. The system of claim 6, wherein the video analytics module is configured to analyze the video data to detect the presence of or movement by an object prior to identifying the object as the person.

12. The system of claim 6, wherein the alert module is configured to format the alert based on an identity of the recipient of the alert.

13. The system of claim 6, wherein the alert module is configured to define the alert to include video data of the monitored premise associated with a time period including at least one of a time period preceding the alarm condition or a time period subsequent the alarm condition.

14. The system of claim 6, wherein the alert module is configured to define the alert to include video data of the monitored premise associated with a time period preceding the alarm condition for transmission directly to at least one of a law enforcement authority or a centralized security station of a security service provider in response to the video analytics module recognizing the alarm condition as an emergency situation.

15. The system of claim 6, wherein the alert module is configured to define the alert to include video information that is at least one of compressed or encoded in a specific manner based on an identity of the recipient.

16. The system of claim 6, wherein the authorization level is associated with the monitored premise.

17. The system of claim 6, wherein the authorization level is associated with a specific time period.

25. The method of claim 6, wherein the user-defined profile includes transmission limitations associated with the at least one recipient.

26. The system of claim 6, wherein the user-defined profile is from a plurality of user-defined profiles, each user-defined profile from the plurality of user-defined profiles includes parameters associated with an authorization level of the person based at least in part on at least one of the identity of the person, a schedule associated with the person, a time of a day, a day of a week, a day of a month, or a time period.

27. The system of claim 6, wherein the video analytics module is collocated with the video source.

34. The system of claim 6, wherein the video analytics module is configured to receive a signal from a sensor associated with an event, the video analytics module configured to determine, based on the authorization level and the alarm signal, that the person is unauthorized.

28. A method comprising:

receiving from a first alarm sensor at a monitored premise a first alarm signal associated with an object at the monitored premise;

receiving from a second alarm sensor at a monitored premise a second alarm signal associated with the object at the monitored premise;

receiving video data of the monitored premise from a video source;

defining a direction of motion associated with the object based on the first alarm signal and the second alarm signal;

conducting video analytics on the video data to confirm the direction of motion associated with the object as an unauthorized direction based at least in part on a profile;

encoding a first portion of the video data using a first level of encoding to produce encoded video data;

encoding a second portion of the video data different from the first portion using a second level of encoding, the first level of encoding different from the second level of encoding; and

sending, based on the direction of motion associated with the object being an unauthorized direction, an alert, including a representation of the encoded video data, indicating the existence of an alarm condition.

29. The method of claim 28, wherein the profile includes sensitivity parameters associated with the object, the conducting video analytics includes rejecting the object at least based on the sensitivity parameters.

30. The method of claim 28, wherein the conducting video analytics includes detecting that one or more objects have been removed from the monitored premise.

31. The method of claim 28, wherein the profile includes control parameters associated with the object, the conducting video analytics includes detecting one or more stationary objects based at least in part on the control parameters.

32. The method of claim 28, wherein the conducting video analytics includes estimating a speed associated with the object.