Apparatus and methods for alarm verification based on image analytics

• US 9,922,514 B2
• Filed: 12/04/2015
• Issued: 03/20/2018
• 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): ANSARI, TAHMINA N
• Application Number:
  US14/959,595
• Publication Number:
  US 20160321889A1
• Time in Patent Office: 837 Days
• Field of Search: None
• 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 non-transitory processor-readable medium storing code representing instructions to be executed by a processor, the code comprising code to cause the processor to:

receive from an image capture device a first image and a second image both associated with a monitored premise;

generate blob data based on both the first image and the second image;

classify an object in both the first image and the second image based on the blob data to produce a classified object identifier;

detect a criterion of the object based on the classified object identifier, the criterion being unique to the object from within a set of objects;

identify a predefined user authorization profile based on the criterion;

determine whether the object is authorized to access the monitored premise based on the predefined user authorization profile; and

send to a compute device a signal representing an alarm event in response to determining that the object is not authorized to access the monitored premise.

2. The non-transitory processor-readable medium of claim 1, wherein the classified object identifier identifies the object as one of a person, vehicle, or animal.

3. The non-transitory processor-readable medium of claim 1, wherein the classified object identifier identifies the object as a person,

the code to cause the processor to detect the criterion includes code to cause the processor to conduct facial recognition of the person, the criterion being associated with facial characteristics of the person.

4. The non-transitory processor-readable medium of claim 1, wherein the classified object identifier identifies the object as a person, the predefined user authorization profile including a time period during which the person is authorized to access the monitored premise,

the code to cause the processor to detect the criterion includes code to cause the processor to conduct facial recognition of the person, the criterion being associated with facial characteristics of the person,

the code to cause the processor to determine includes code to cause the processor to determine that the person is not authorized to access the monitored premise when a time at which the image was captured is not within the time period.

5. The non-transitory processor-readable medium of claim 1, wherein the code to cause the processor to receive the first image and the second image includes code to cause the processor to receive from the image capture device a video associated with the monitored premise, the video including the first image and the second image, the code to cause the processor to classify the object includes code to cause the processor to classify the object at a second time, the code further comprising code to cause the processor to:

analyze, at a first time before the second time, the video to detect motion at the monitored premise,

the code to cause the processor to classify the object includes code to classify the object in response to the detected motion at the monitored premise.

6. The non-transitory processor-readable medium of claim 1, the code further comprising code to cause the processor to:

select a first level of encoding for the object;

encode a portion of at least one of the first image or the second image including the object based on the first level of encoding to produce first encoded image data;

encode a portion of the at least one of the first image or the second image excluding the object based on a second level of encoding to produce second encoded image data, the second level of encoding being different than the first level of encoding; and

send to the compute device a signal representing the first encoded image data.

7. The non-transitory processor-readable medium of claim 1, wherein the classified object identifier identifies the object as a vehicle, the code further comprising code to cause the processor to:

send a signal to the image capture device representing instructions to modify image capture parameters of the image capture device based on the criterion of the object.

8. The non-transitory processor-readable medium of claim 1, wherein the classified object identifier identifies the object as a vehicle, the code further comprising code to cause the processor to:

send a signal to the image capture device representing instructions to modify image capture parameters of the image capture device based on the criterion of the object, the image capture device having modified image capture parameters in response to receiving the instructions to modify the image capture parameters;

receive from the image capture device having the modified image capture parameters a third image associated with the monitored premise and including a representation of the object; and

detect the criterion of the object based on the third image.

9. The non-transitory processor-readable medium of claim 1, wherein the classified object is a vehicle, the criterion is an estimated speed at which the vehicle is traveling, the code further comprising code to cause the processor to:

send a signal to the image capture device representing instructions to modify an exposure time period of the image capture device based on the estimated speed.

10. The non-transitory processor-readable medium of claim 1, wherein the first image is captured at a first time and the second image is captured at a second time after the first time, the code further comprising code to cause the processor to:

conduct image analysis on both the first image and the second image to identify a change between the first image and the second image,

the code to cause the processor to classify the object includes code to cause the processor to classify the object based on the identified change.

18. The non-transitory processor-readable medium of claim 1, wherein the blob data includes at least one of a geometric property or an appearance property of the object.

19. The non-transitory processor-readable medium of claim 1, wherein the classified object identifier identifies the object as a vehicle, the code further comprising code to cause the processor to:

send a signal to the image capture device representing instructions to modify at least one of a tilt, sweep, or brightness compensation parameter of the image capture device based on at least one of the classified object identifier or the criterion of the object.

11. A non-transitory processor-readable medium storing code representing instructions to be executed by a processor, the code comprising code to cause the processor to:

receive from a video capture device a video both associated with a monitored premise and captured during an event time period;

detect motion of an object at the monitored premise based on the video;

classify, in response to the detected motion, the object as a person;

analyze a set of pixels classified as the person to determine an identity of the person;

determine, based on a predefined user profile (1) associated with the identity of the person, and (2) indicating an authorization time period during which the person is authorized to access the monitored premise, whether the person is authorized to access the monitored premise during the event time period; and

send to a compute device a signal representing, an alarm event when it is determined that the person is not authorized to access the monitored premise during the event time period, the determination that the person is not authorized being based on a comparison of the event time period to the authorization time period.

12. The non-transitory processor-readable medium of claim 11, the code further comprising code to cause the processor to:

receive from a sensor separate from the video capture device a criterion uniquely associated with the person;

match the criterion to a criterion of the predefined user profile to produce a positive match; and

authorize the person for access to the monitored premise based on the positive match.

13. The non-transitory processor-readable medium of claim 11, the code further comprising code to cause the processor to:

receive from a sensor separate from the video capture device a criterion uniquely associated with the person;

match the criterion to a criterion of the predefined user profile to produce a positive match; and

authorize the person for access to the monitored premise based on both the positive match and a temporal restriction of the predefined user profile.

14. The non-transitory processor-readable medium of claim 11, wherein the alarm event is a first alarm event, the code further comprising code to cause the processor to:

receive from a sensor separate from the video capture device a criterion uniquely associated with a person from within a set of people;

compare the criterion uniquely associated with the person to a criterion of the predefined user profile; and

send to the compute device a signal representing a second alarm event when the criterion uniquely associated with the person does not match the identity of the person.

15. The non-transitory processor-readable medium of claim 11, wherein the alarm event is a first alarm event, the code further comprising code to cause the processor to:

receive from a card swipe sensor separate from the video capture device a criterion uniquely associated with a person from within a set of people;

compare the criterion uniquely associated with the person to a criterion of the predefined user profile; and

send to the compute device a signal representing a second alarm event when the criterion uniquely associated with the person does not match the criterion of the predefined user profile.

16. The non-transitory processor-readable medium of claim 11, wherein the compute device is a first compute device, the code further comprising code to cause the processor to:

send, to a second compute device separate from the first compute device, a signal representing at least a portion of the video; and

receiving, from the second compute device, a signal representing verification of the identity of the person,

the code to cause the processor to determine whether the person is authorized to access the monitored premise includes code to cause the processor to determine whether or not the person is authorized to access the monitored premise based on the signal representing verification of the identity of the person.

17. The non-transitory processor-readable medium of claim 11, wherein the code to cause the processor to analyze the set of pixels to determine the identity of the person includes code to cause the processor to analyze the set of pixels classified as the person to determine the identity of the person based on the predefined user profile.

20. The non-transitory processor-readable medium of claim 11, wherein the video is a first video, the event time period is a first event time period, the code further comprising code to cause the processor to:

determine based on the predefined user profile that the person is not authorized to access the monitored premise during the first event time period;

send to the compute device the signal representing the alarm event in response to determining that the person is not authorized to access the monitored premise during the first event time period;

receive from the video capture device a second video associated with the monitored premise and captured during a second event time period different from the first event time period;

detect motion of the object at the monitored premise based on the second video;

analyze a set of pixels classified as the person to determine the identity of the person,

determine, based on the predefined user profile associated with the identity of the person, that the person is authorized to access the monitored premise during the second event time period; and

send a signal representing authorization of the person during the second event tune period.