Systems and methods for automated image-based auditing of equipment cabinets

Patent metadata

Field	Value
Publication number	US-12159368-B2
Application number	US-202117354897-A
Country	US
Kind code	B2
Filing date	Jun 22, 2021
Priority date	Jun 22, 2020
Publication date	Dec 3, 2024
Grant date	Dec 3, 2024

Abstract

An electronic device for automated image-based auditing of equipment cabinets may include a memory storing an imaging computer program; and a computer processor. The imaging computer program, when executed by the computer processor, may cause the computer processor to perform the following: receive a plurality images from an image capture device on a carriage, wherein the image capture device is configured to traverse an equipment cabinet and capture the plurality of images of equipment in the equipment cabinet; generate a single image by stitching the plurality of images together; receive data from a sensor on the carriage, wherein the sensor is configured to capture data from the equipment in the equipment cabinet; associate the data with a location in the equipment cabinet; compare the single image and the data to an expected image and expected data; and output a result of the comparison.

First claim

What is claimed is:

1. A system, comprising:
a frame comprising a base, a top support, and a plurality of vertical supports;
a gantry movably received on the vertical supports, wherein the gantry is movable in a vertical direction;
a carriage movably received on the gantry, wherein the carriage is movable in a horizontal direction, the carriage comprising:
a plurality of sensors received on the carriage, wherein at least one of the plurality of sensors comprises an imaging device that captures a plurality of images of equipment in an equipment cabinet for an equipment cabinet build and a sensor that captures data from the equipment in the equipment cabinet build;
a motor mounted on the carriage that moves the carriage in the horizontal direction; and
a controller that controls operation of the imaging device and the plurality of sensors and the motor; and

an imaging computer program executed on a computing device that is configured to:
receive the plurality images and stitch the plurality of images together to form a single image of the equipment cabinet;
receive the data and associate the data with a location on the equipment cabinet;
compare the single image and the data to an expected image and expected data for the equipment cabinet build; and
output a result of the comparison.

2. The system of claim 1 , wherein the imaging device comprises a daylight camera or a thermal imaging camera.

3. The system of claim 1 , wherein the plurality of sensors comprise one or more of a Radio Frequency Identifier (RFID) reader, a barcode scanner, a temperature sensor, a humidity sensor, a light sensor, a velometer, an anemometer, a non-contact voltage tester, a hall effect sensor, a Light Detection and Ranging (LIDAR) sensor, a ultrasonic sensor, and a Near Field Communication (NFC) reader.

4. The system of claim 1 , wherein the controller receives information for the equipment cabinet build and controls the operation of the plurality of sensors and the motor based on the information for the equipment cabinet build.

5. The system of claim 1 , wherein the imaging computer program further generates a composite image comprising the single image and the data from the plurality of sensors.

6. The system of claim 1 , wherein the expected image is based on machine learning from imaging at least one prior equipment cabinet.

7. The system of claim 1 , wherein the expected image is based on build information for the equipment cabinet build received by the imaging computer program.

8. The system of claim 1 , wherein the carriage is configured to tilt and/or pan relative to the gantry.

9. A method, comprising:
controlling, at a controller, a motor mounted on a carriage to move relative to an equipment cabinet;
controlling, by the controller, an imaging device to capture a plurality of images of equipment in the equipment cabinet;
controlling, by the controller, at least one sensor to capture data from the equipment in the equipment cabinet; and
communicating the plurality of images and the data to an imaging computer program;
wherein the imaging computer program is configured to:
receive the plurality images and stitch the plurality of images together to form a single image of the equipment cabinet;
receive the data and associate the data with a location on the equipment cabinet;
compare the single image and the data to an expected image and expected data for an equipment cabinet build; and
output a result of the comparison.

10. The method of claim 9 , wherein the imaging device comprises a daylight camera or a thermal imaging camera.

11. The method of claim 9 , wherein the plurality of sensors comprise one or more of a Radio Frequency Identifier (RFID) reader, a barcode scanner, a temperature sensor, a humidity sensor, a light sensor, a velometer, an anemometer, a non-contact voltage tester, a hall effect sensor, a Light Detection and Ranging (LIDAR) sensor, a ultrasonic sensor, and a Near Field Communication (NFC) reader.

12. The method of claim 9 , wherein the controller receives information for the equipment cabinet build and controls the plurality of sensors and a motor based on the information for the equipment cabinet build.

13. The method of claim 9 , wherein the imaging computer program further generates a composite image comprising the single image and the data from the sensors.

14. The method of claim 9 , wherein the expected image is based on machine learning from imaging at least one prior equipment cabinet.

15. The method of claim 9 , wherein the expected image is based on build information for the equipment cabinet build received by the imaging computer program.

16. An electronic device, comprising:
a memory storing an imaging computer program; and
a computer processor;
wherein the imaging computer program, when executed by the computer processor, causes the computer processor to perform the following:
receive a plurality of images from an image capture device on a carriage, wherein a motor mounted on the carriage is configured to move the image capture device to traverse an equipment cabinet and capture the plurality of images of equipment in the equipment cabinet;
generate a single image by stitching the plurality of images together;
receive data from a sensor on the carriage, wherein the sensor is configured to capture data from the equipment in the equipment cabinet;
associate the data with a location in the equipment cabinet;
compare the single image and the data to an expected image and expected data; and
output a result of the comparison.

17. The electronic device of claim 16 , wherein the expected image is based on machine learning from imaging at least one prior equipment cabinet.

18. The electronic device of claim 16 , wherein the expected image is based on build information for an equipment cabinet build for the equipment cabinet.

19. The electronic device of claim 16 , wherein the image capture device comprises a daylight camera or a thermal imaging camera.

20. The electronic device of claim 16 , wherein the comprises a Radio Frequency Identifier (RFID) reader, a barcode scanner, a temperature sensor, a humidity sensor, a light sensor, a velometer, an anemometer, a non-contact voltage tester, a hall effect sensor, a Light Detection and Ranging (LIDAR) sensor, a ultrasonic sensor, and a Near Field Communication (NFC) reader.

Assignees

• Jpmorgan Chase Bank Na

Inventors

• Cox Jacob
• Newnam Robert S
• Du Zhen

Classifications

• G06N20/00

  Machine learning · CPC title

• G06T2207/10052

  Images from lightfield camera · CPC title

• G06T2207/10048

  Infrared image · CPC title

• H04L67/12

  specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title

• G06T7/001

  using an image reference approach · CPC title