System and method of image analysis for automated asset identification

• US 9,710,720 B2
• Filed: 04/29/2015
• Issued: 07/18/2017
• Est. Priority Date: 04/29/2015
• Status: Active Grant

• Current Assignee: GE Global Sourcing LLC (Westinghouse Air Brake Technologies Corporation)
• Original Assignee: General Electric Company
• Inventors: Jeffrey, Brian David, Mitti, Aaron Richard
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US14/700,078
• Publication Number:
  US 20160321513A1
• Time in Patent Office: 811 Days
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names

Abstract

A system and method are provided that capture an image of an asset and analyze the captured image to identify an indicium on the asset. The indicium is used, after identification, to identify the asset. The system may also be configured to identify a type of asset, to track the asset, to verify a manifest for a group of assets, or to identify damage to an asset based on comparing the captured image of the asset with a previously captured image of the asset.

Claims

1. A system comprising:

a device that is configured to capture and store an image on a memory, wherein the image is of a portion of a consist that couples to a rail system and each portion of the consist includes an indicium;

one or more software modules that are configured to be executed by one or more processors for enabling the one or more processors to receive the image from the memory, determine a type of rail vehicle in the portion of the consist based on the image, determine an indicia location based on the type of rail vehicle that is determined, and perform a first image analysis on the image based on the indicia location that is determined, wherein the first image analysis results in identifying the indicium from the image;

the one or more software modules further configured to enable the one or more processors to query a data store with the indicium to receive a query result that is a data representative of the portion of the consist, wherein the data representative of the portion of consist includes a previously stored image of the portion of the consist;

the one or more software modules also configured to enable the one or more processors to perform a second image analysis on the image and the previously stored image, wherein the second image analysis is a comparison between the image and the previously stored image of the portion of the consist which results in identifying a change to an area of the consist;

the one or more software modules also configured to enable the one or more processors to store, on the memory, the following data upon capture of the image of the portion of the consist by the device;

a time stamp of when the image was captured, and a geographic location of where the image was captured;

the one or more software modules further configured to enable the one or more processors to track an inventory of one or more consists for a rail yard based on evaluating the time stamp and the geographic location and respond to a query about the consist by communicating a query result that includes the image of the consist and that includes a geographic location of where the image was captured.

2. The system of claim 1, wherein each portion of the consist comprises one or more rail vehicles.

3. The system of claim 2, wherein the one or more software modules are further configured to enable the one or more processors to identify the one or more rail vehicles by analyzing a least a portion of the image corresponding to the determined indicia to determine the indicium that is on the vehicle.

4. The system of claim 3, wherein the one or more software modules are further configured to enable the one or more processors to:

associate and store the image with the identification of the identified one or more rail vehicles and with at least one of a location where the image was captured or a time when the image was captured.

5. The system of claim 2, wherein the one or more software modules are further configured to enable the one or more processors to:

receive a reference manifest for a plurality of associated rail vehicles, wherein the reference manifest defines the plurality of associated rail vehicles,

generate an image-based manifest for the plurality of associated rail vehicles by identifying each rail vehicle based on images captured by the device,

compare the reference manifest and the image-based manifest to identify differences, and

communicate a notification regarding the differences.

6. The system of claim 2, wherein the one or more software modules are further configured to enable the one or more processors to:

retrieve a previous image of the portion of the consist from a database,

compare the image to the retrieved previous image,

determine an indication of at least one of wear or damage of the one or more rail vehicles based on the comparison of the image and the previous image, and

transmit a notification regarding the indication of wear or damage of the one or more rail vehicles.

7. The system of claim 6, wherein the indication of wear or damage of the one or more rail vehicles is one of wear on a wheel of the one or more rail vehicles or a dent on the one or more rail vehicles.

8. The system of claim 6, wherein the indication of wear or damage of the one or more rail vehicles is whether a seal is intact on a portion of the one or more rail vehicles.

9. The system of claim 6, wherein the one or more software modules are further configured to enable the one or more processors to compensate for environmental variance between the image and the retrieved previous image when comparing the image to the retrieved previous image, wherein the variance is at least one of a time of day, a lighting change, or a state of weather, and wherein the state of weather is at least one of a presence of dust, leaves, smoke, snow, rain, or fog.

10. The system of claim 2, wherein the one or more software modules are further configured to enable the one or more processors to:

activate the device to capture a second image of the portion of the consist that includes the determined indicia location; and

identify the one or more rail vehicles by analyzing at least a portion of the second image to determine the indicium that is on the one or more rail vehicles.

11. The system of claim 2, wherein the one or more software modules are further configured to enable the one or more processors to:

activate the device to capture the image in response to receiving a signal associated with the portion of the consist being proximate to the device.

12. The system of claim 11, wherein the signal is from a switch coupled to the rail system that detects the portion of the consist being proximate to the device.

13. The system of claim 11, wherein the signal is from a location tracking component of the one or more rail vehicles that detects the portion of the consist being proximate to the device.

14. The system of claim 1, wherein the one or more software modules are further configured to enable the one or more processors to determine the type of rail vehicle by analyzing the image of the portion of the consist.

15. The system of claim 14, wherein the one or more rail vehicles are at least one of a tank car, a box car, a hopper car, a flat car, or a locomotive.

16. The system of claim 14, wherein the one or more rail vehicles include an intermodal container.

17. The system of claim 1, wherein the one or more software modules are further configured to enable the one or more processors to determine the type of rail vehicle further based upon receipt of an electronically communicated asset type identification.

18. The system of claim 1, wherein the one or more software modules are further configured to enable the one or more processors to access a database containing an association of types of rail vehicles with indicia locations for the types of rail vehicles.

19. The system of claim 1, wherein the device is stationary and positioned proximate to a route over which the portion of the consist travels.

20. The system of claim 1, wherein the device is a mobile device.