Machine learning-based device placement and configuration service

Patent metadata

Field	Value
Publication number	US-10939031-B2
Application number	US-202016896366-A
Country	US
Kind code	B2
Filing date	Jun 9, 2020
Priority date	Oct 17, 2018
Publication date	Mar 2, 2021
Grant date	Mar 2, 2021

Abstract

A method, a device, and a non-transitory storage medium are described in which a machine learning-based device placement and configuration service is provided. The machine learning-based device placement and configuration system uses regression models calculated from installation and performance data. The regression model includes data associated with sites at which video cameras were previously installed and tested for detection accuracy levels possibly associated with a service area. With these generated models, information about the physical space, and desired performance criteria, designers optimize camera number, camera placement, and geo-location camera parameters. The device placement and configuration service may find an optimal camera placement and geo-location camera parameter set which satisfy certain criteria. The geo-location parameters include position, height, heading, pitch, and roll. Subsequent to the installation of the video cameras using the calculated geo-location parameters, the system may verify accuracy of detection of the service area, and update the regression model.

First claim

What is claimed is:

1. A method comprising:
receiving, by a network device, one or more locales of a candidate site at which one or more virtual video cameras are to be virtually affixed;
receiving, by the network device, geo-location parameters for the one or more virtual video cameras;
calculating, by the network device, an anticipated coverage value of the candidate site based on the geo-location parameters, a regression model, map information, and one or more fields of view for the one or more virtual video cameras;
determining, by the network device, that the anticipated coverage value satisfies a target coverage value; and
using the geo-location parameters to install and test one or more video cameras at the candidate site in response to determining that the anticipated coverage value satisfies the target coverage value.

2. The method of claim 1 , wherein the geo-location parameters include location, height, heading, pitch, and roll values.

3. The method of claim 1 , wherein the regression model stores data associated with parameters derived from previously installed and tested video cameras at sites.

4. The method of claim 1 , further comprising:
calculating, by the network device, the one or more fields of view for the one or more virtual video cameras based on the map information, the geo-location parameters, and video camera characteristic information pertaining to the one or more video cameras.

5. The method of claim 1 , further comprising:
downloading, by the network device after the using, the geo-location parameters to the one or more video cameras that are installed at the candidate site;
receiving, by the network device, one or more video feeds of a service area from the one or more video cameras; and
annotating, by the network device, the one or more video feeds.

6. The method of claim 5 , further comprising:
calculating, by the network device, a coverage value based on the annotating.

7. The method of claim 6 , further comprising:
updating, by the network device, the regression model based on the coverage value and the annotating.

8. The method of claim 1 , wherein the map information includes a three-dimensional map of the candidate site, and wherein the target coverage value includes an amount of coverage of a service area or a portion of the service area that supports a service to be provided at the candidate site.

9. A network device comprising:
a processor, wherein the processor is configured to:
receive one or more locales of a candidate site at which one or more virtual video cameras are to be virtually affixed;
receive geo-location parameters for the one or more virtual video cameras;
calculate an anticipated coverage value of the candidate site based on the geo-location parameters, a regression model, map information, and one or more fields of view for the one or more virtual video cameras;
determine that the anticipated coverage value satisfies a target coverage value; and
use the geo-location parameters to install and test one or more video cameras at the candidate site in response to a determination that the anticipated coverage value satisfies the target coverage value.

10. The network device of claim 9 , wherein the geo-location parameters include location, height, heading, pitch, and roll values.

11. The network device of claim 9 , wherein the regression model stores data associated with parameters derived from previously installed and tested video cameras at sites.

12. The network device of claim 9 , wherein the processor is further configured to:
calculate the one or more fields of view for the one or more virtual video cameras based on the map information, the geo-location parameters, and video camera characteristic information pertaining to the one or more video cameras.

13. The network device of claim 9 , wherein the processor is further configured to:
download, after the using, the geo-location parameters to the one or more video cameras that are installed at the candidate site;
receive one or more video feeds of the service area from the one or more video cameras; and
annotate the one or more video feeds.

14. The network device of claim 13 , wherein the processor is further configured to:
calculate a coverage value based on the annotation.

15. The network device of claim 14 , wherein the processor is further configured to:
update the regression model based on the calculation of the coverage value and the annotation.

16. The network device of claim 9 , wherein the map information includes a three-dimensional map of the candidate site, and wherein the target coverage value includes an amount of coverage of a service area or a portion of the service area that supports a service to be provided at the candidate site.

17. A non-transitory computer-readable storage medium storing instructions executable by a processor of a device, which when executed cause the device to:
receive one or more locales of a candidate site at which one or more virtual video cameras are to be virtually affixed;
receive geo-location parameters for the one or more virtual video cameras;
calculate an anticipated coverage value of the candidate site based on the geo-location parameters, a regression model, map information, and one or more fields of view for the one or more virtual video cameras;
determine that the anticipated coverage value satisfies a target coverage value; and
use the geo-location parameters to install and test one or more video cameras at the candidate site in response to a determination that the anticipated coverage value satisfies the target coverage value.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the geo-location parameters include location, height, heading, pitch, and roll values.

19. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions further comprise instructions, which when executed cause the device to:
calculate the one or more fields of view for the one or more virtual video cameras based on the map information, the geo-location parameters, and video camera characteristic information pertaining to the one or more video cameras.

20. The non-transitory computer-readable storage medium of claim 17 , wherein the regression model stores data associated with parameters derived from previously installed and tested video cameras at sites.

Assignees

• Verizon Patent & Licensing Inc

Inventors

• Herson Andrew W
• Huszar Domonkos
• Horvath Istvan S
• Kennedy Christopher
• Rekeczky Csaba

Classifications

• H04N7/18 Primary

  Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast · CPC title

• H04N23/661 Primary

  Transmitting camera control signals through networks, e.g. control via the Internet · CPC title

• H04N23/64

  Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image · CPC title

• H04N23/631

  Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters · CPC title

• H04N23/90

  Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums · CPC title