Method and system for capturing and storing significant surveillance images

• US 10,559,200 B1
• Filed: 05/01/2018
• Issued: 02/11/2020
• Est. Priority Date: 05/01/2018
• Status: Active Grant

• Current Assignee: Flock Group Inc.
• Original Assignee: Flock Group Inc.
• Inventors: Langley, Garrett, Feury, Matt
• Primary Examiner(s): Hasan, Mainul
• Application Number:
  US15/968,399
• Time in Patent Office: 651 Days
• CPC Class Codes: G06F 1/3296 by lowering the supply or operating voltage
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/82 using neural networks
• 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: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/017 identifying vehicles G08G1/015, G08G1/054 take precedence
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules

Abstract

A method and system for capturing and filtering surveillance images are described. A processor detects motion of an object in a field of view and then generates a plurality of images in response to detecting motion of the object in the field of view. A first filter is then applied to the plurality of images and later, the one or remaining images based on the first filter are stored in a memory device. In response to a triggering event, an energy conserving processor is activated from a sleep mode of operation where the energy conserving processor applies a second filter to the remaining images from the first filter. The energy conserving processor assigns a confidence score to one or more images matching the second filter. With the second filter, the energy conserving processor selects fewer images for RF transmission to a remote image analyzer, resulting in increased power savings.

Claims

1. A computer-implemented method for capturing and filtering surveillance images, the computer-implemented method comprising:

a processor for detecting motion of an object in a field of view;

a processor for generating a plurality of images in response to detecting motion of the object in the field of view;

a processor for applying a first filter to the plurality of images to create a reduced set of images by removing duplicate images after comparing images from prior detection of motion of the object;

a processor for storing the reduced set of images based on the first filter;

a processor for determining if an energy conserving processor should be woken from a sleep mode of operation based on two conditions, a first condition comprising a predetermined amount of time and a second condition comprising an amount of storage for the reduced set of images based on the first filter which were stored by the processor, the processor awaking the energy conserving processor if at least one of the two conditions has been met;

the energy conserving processor becoming activated in response to the processor determining that the energy conserving processor should be woken from its sleep mode of operation based on at least one of the two conditions;

the energy conserving processor applying a second filter to the reduced set of images from the first filter;

the energy conserving processor assigning a confidence score to one or more images matching the second filter; and

the energy conserving processor designating the one or more images matching the second filter for transmission over a computer network.

2. The computer-implemented method of claim 1, wherein the first filter comprises a difference comparison among the plurality of images.

3. The computer-implemented method of claim 1, wherein the second filter comprises a filtering algorithm based on a neural network.

4. The computer-implemented method of claim 1, further comprising the energy conserving processor transmitting the one or more images matching the second filter over a cellular telephone network.

5. The computer-implemented method of claim 1, wherein the object comprises a vehicle.

6. The computer-implemented method of claim 5, wherein the vehicle has a license plate.

7. The computer-implemented method of claim 1, wherein the one or more images matching the second filter are transmitted over the computer network to a remote image analyzer.

8. The computer-implemented method of claim 7, wherein the remote image analyzer determines on or more image settings based on the one or more images matching the second filter.

9. The computer-implemented method of claim 3, wherein the remote image analyzer determines one or more updates for weightings used in the neural network.

15. The computer-implemented system of claim 5, wherein the vehicle has a license plate.

20. The system of claim 1, wherein the camera module comprises a processor different from the energy conserving processor.

10. A computer-implemented system for capturing and filtering surveillance images, the computer-implemented system comprising:

means for detecting motion of an object in a field of view;

means for generating a plurality of images in response to detecting motion of the object in the field of view;

means for applying a first filter to the plurality of images to create a reduced set of images by removing duplicate images after comparing images from prior detection of motion of the object;

means for storing the reduced set of based on the first filter;

means for determining if an energy conserving processor should be woken from a sleep mode of operation based on two conditions, a first condition comprising a predetermined amount of time and a second condition comprising an amount of storage for the reduced set of images based on the first filter which were stored by the processor, the processor awaking the energy conserving processor if at least one of the two conditions has been met;

the energy conserving processor becoming activated in response to the means for determining that the energy conserving processor should be woken from its sleep mode of operation based on at least one of the two conditions;

the energy conserving processor applying a second filter to the reduced set of images from the first filter;

the energy conserving processor assigning a confidence score to one or more images matching the second filter; and

the energy conserving processor designating the one or more images matching the second filter for transmission over a computer network.

11. The computer-implemented system of claim 10, wherein the first filter comprises a difference comparison among the plurality of images.

12. The computer-implemented system of claim 10, wherein the second filter comprises a filtering algorithm based on a neural network.

13. The computer-implemented system of claim 10, wherein the energy conserving processor transmits the one or more images matching the second filter over a cellular telephone network.

14. The computer-implemented system of claim 10, wherein the object comprises a vehicle.

16. A system for capturing and filtering surveillance images, the system comprising:

a device for detecting motion of an object in a field of view;

a camera module for generating a plurality of images in response to detecting motion of the object in the field of view;

the camera module applying a first filter to the plurality of images to create a reduced set of images by removing duplicate images after comparing images from prior detection of motion of the object;

the camera module determining if an energy conserving processor should be woken from a sleep mode of operation based on two conditions, a first condition comprising a predetermined amount of time and a second condition comprising an amount of storage for the reduced set of images based on the first filter which were stored by the processor, the processor awaking the energy conserving processor if at least one of the two conditions has been met;

a memory device for storing the reduced set of images based on the first filter;

the energy conserving processor becoming activated in response to the processor determining that the energy conserving processor should be woken from its sleep mode of operation based on at least one of the two conditions;

the energy conserving processor applying a second filter to the reduced set of images from the first filter;

the energy conserving processor assigning a confidence score to one or more images matching the second filter; and

the energy conserving processor designating the one or more images matching the second filter for transmission over a computer network.

17. The system of claim 16, wherein the first filter comprises a difference comparison among the plurality of images.

18. The system of claim 16, wherein the second filter comprises a filtering algorithm based on a neural network.

19. The system of claim 16, wherein the energy conserving processor transmits the one or more images matching the second filter over a cellular telephone network.