Asset identification and tracking system

Patent metadata

Field	Value
Publication number	US-11875284-B2
Application number	US-202117152631-A
Country	US
Kind code	B2
Filing date	Jan 19, 2021
Priority date	Apr 30, 2019
Publication date	Jan 16, 2024
Grant date	Jan 16, 2024

Abstract

An asset identification and tracking system includes one or more monitoring units configured to monitor at least one designated area. Each of the monitoring units includes an imaging device and one or more processors. The imaging device is configured to generate image data depicting one or more mobile assets that move through the at least one designated area. The one or more processors are operably coupled to the imaging device and configured to analyze the image data to detect and decipher one or more identifiers that are displayed on a particular mobile asset of the one or more mobile assets that move through the at least one designated area. The one or more processors are further configured to generate a detection message that includes the one or more identifiers for communication to an asset control system.

First claim

What is claimed is:

1. A system comprising:
an imaging device configured to generate image data depicting one or more mobile assets that move through a designated area; and
one or more processors configured to analyze the image data to detect one or more non-alphanumeric graphic identifiers of a particular mobile asset of the one or more mobile assets, each of the one or more non-alphanumeric graphic identifiers representing a feature that differentiates the particular mobile asset from at least some other mobile assets that move through the designated area without individually uniquely identifying the particular mobile asset, the one or more processors configured to compare the one or more non-alphanumeric graphic identifiers of the particular mobile asset that are detected to information in an inventory database associated with each of multiple identified assets to positively identify the particular mobile asset as a first identified asset of the multiple identified assets based on a level of match between the one or more non-alphanumeric graphic identifiers and the information in the inventory database associated with the first identified asset.

2. The system of claim 1 , wherein the one or more processors further are configured to generate a detection message for communication to an asset control system, and the detection message includes the one or more non-alphanumeric graphic identifiers.

3. The system of claim 1 , wherein the one or more processors are configured to update the inventory database, in response to positively identifying the particular mobile asset as the first identified asset, to reflect that the first identified asset was located in the designated area at a time that the image data was generated depicting the one or more non-alphanumeric graphic identifiers.

4. The system of claim 2 , wherein the one or more processors are configured to generate the detection message to include information relating to at least one of a direction of travel of the particular mobile asset or an orientation of the particular mobile asset.

5. The system of claim 2 , wherein the one or more processors are configured to detect and decipher an alphanumeric assigned identifier on the particular mobile asset by analyzing the image data, and the one or more processors generate the detection message to include both the alphanumeric assigned identifier and the one or more non-alphanumeric graphic identifiers associated with the particular mobile asset.

6. The system of claim 1 , wherein at least one of the one or more non-alphanumeric graphic identifiers relates to an occupant of the particular mobile asset and includes one or more of a face, clothing, fashion accessory, outerwear, head gear, footwear, carry bag, or gait of the occupant.

7. The system of claim 1 , wherein the one or more non-alphanumeric graphic identifiers comprise one or more of a dent, scratch, graffiti, rust spot, paint scheme, discoloration, cargo type, accessory type, or mud splatter.

8. The system of claim 1 , wherein the one or more processors are configured to detect multiple non-alphanumeric graphic identifiers of the particular mobile asset by analyzing the image data, and are configured to positively identify the particular mobile asset as the first identified asset by a combination of the multiple non-alphanumeric graphic identifiers matching the information associated with the first identified asset to an extent that meets or exceeds a determined combination threshold.

9. The system of claim 1 , wherein the particular mobile asset is a rail vehicle.

10. The system of claim 1 , wherein the one or more processors are configured to analyze the image data to detect an alphanumeric assigned identifier that is displayed on the particular mobile asset, and the alphanumeric assigned identifier on the particular mobile asset is unique to the particular mobile asset.

11. The system of claim 1 , wherein the one or more processors are configured to detect the one or more non-alphanumeric graphic identifiers by inputting image frames of the image data one at a time as inputs in a forward propagation direction through layers of artificial neurons in an artificial neural network.

12. The system of claim 11 , wherein the artificial neural network is trained to determine a type of the particular mobile asset that moves through the designated area, and the one or more processors are configured to analyze the image data to detect the one or more non-alphanumeric graphic identifiers by accessing a look-up table that associates the type of the particular mobile asset with an anticipated location of the one or more non-alphanumeric graphic identifiers on the particular mobile asset.

13. The system of claim 1 , wherein the one or more processors are configured to compare the one or more non-alphanumeric graphic identifiers of the particular mobile asset that are detected to the information in the inventory database in response an inability of the one or more processors to detect or decipher an alphanumeric identifier on the particular mobile asset in the image data, the alphanumeric identifier uniquely assigned to the particular mobile asset.

14. A method comprising:
generating image data depicting one or more mobile assets that move through a designated area;
analyzing the image data to detect one or more non-alphanumeric graphic identifiers of a particular mobile asset of the one or more mobile assets, each of the one or more non-alphanumeric graphic identifiers representing a feature that differentiates the particular mobile asset from at least some other mobile assets that move through the designated area without individually uniquely identifying the particular mobile asset;
comparing the one or more non-alphanumeric graphic identifiers atoll of the particular mobile asset that are detected to information in an inventory database associated with each of multiple identified assets; and
positively identifying the particular mobile asset as a first identified asset of the multiple identified assets based on a level of match between the one or more non-alphanumeric graphic identifiers and the information in the inventory database associated with the first identified asset.

15. The method of claim 14 , further comprising generating a detection message for communication to an asset control system, the detection message including the one or more non-alphanumeric graphic identifiers.

16. The method of claim 14 , further comprising analyzing the image data to detect an alphanumeric assigned identifier that is displayed on the particular mobile asset, and the alphanumeric assigned identifier on the particular mobile asset is unique to the particular mobile asset.

17. The method of claim 14 , wherein the designated area is a first designated area and
the method comprises tracking the particular mobile asset from the first designated area to a second designated area based on analyzing second image data that depicts the second designated area and detecting the same one or more non-alphanumeric graphic identifiers in the second image data.

18. The method of claim 14 , further comprising determining one or more of a type of the particular mobile asset or a business entity that operates the particular mobile asset, and accessing a look-up table that associates one or more of the type of the particular mobile asset or the business entity with an anticipated location of the one or more non-alphanumeric graphic identifiers on the particular mobile asset, the one or more non-alphanumeric graphic identifiers detected by analyzing the

Assignees

• Transp Ip Holdings Llc

Inventors

• Brooks James D
• Zhao Guangliang
• Ge Weina
• Tu Peter
• Woo Derek K
• Rush Daniel J
• Franco Adam

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06Q10/0877

  by inventory control or reporting using inventory tracking or counting · CPC title

• G06Q10/04 Primary

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title

• B61L25/028

  Determination of vehicle position and orientation within a train consist, e.g. serialisation · CPC title

• B61L25/04

  Indicating or recording train identities · CPC title