Rail feature identification system

Patent metadata

Field	Value
Publication number	US-11893727-B2
Application number	US-202117508984-A
Country	US
Kind code	B2
Filing date	Oct 23, 2021
Priority date	Oct 23, 2020
Publication date	Feb 6, 2024
Grant date	Feb 6, 2024

Abstract

The present disclosure includes systems, devices, and methods for identifying, detecting, and/or tracking rail features. In some aspects, a system includes a camera and a computer having at least one memory, at least one processor configured to receive a plurality of images from the camera, and for each of the images: assigning a location identifier and identifying one or more rail features that correspond to one of a plurality of predetermined rail features. In some systems, the at least one processor is configured to determine a location of each of the one or more identified rail features.

First claim

The invention claimed is:

1. A rail vehicle comprising:
a frame coupled to a plurality of rail wheels configured to move along a rail track; and
a railroad track feature detection system coupled to the frame, the feature detection system comprising:
a camera coupled to the frame and positioned such that the camera is configured to capture a plurality of images of a rail track as the rail vehicle moves along the rail track; and
a computer having: at least one memory comprising instructions; and at least one processor configured to execute the instructions, wherein the instructions cause the at least one processor to:
receive the plurality of images, and for each of the images:
assign a location identifier;
detect one or more rail features;
identify the one or more rail features as a relevant rail feature from a dataset of predetermined rail features; and
assign a feature identifier to each identified rail feature;

based on the location identifier and the feature identifier:
determine a geographical location of the one or rail more features; and
track the one or more rail features;

assign a first location identifier to a first image of the plurality of images;
identify, in the first image, the one or more rail features;
assign a second location identifier to a second image of the plurality of images;
compare the first location identifier with the second location identifiter to determine a first displacement distance between the identified rail features in the first image;
based on the first displacement distance, determine if one or more rail features in the second image correspond to one of the one or more identified rail features in the first image; and
based on the determintion that:
a first subset of the one or more rail features in the second image correspond to at least one of the one or more identified rail features in the first image, setting the first subset as detected rail features and re-identifying the first subset of the one or more rail features; and
a second subset of the one or more features in the second image does not correspond to at least one of the one or more identified rail features in the first image, setting the second subset as detected rail features and identifying, in the first image, the second subset of the one or more rail features.

2. The rail vehicle of claim 1 , wherein the instructions include a convolutional neural network.

3. The rail vehicle of claim 1 , wherein:
the processor is configured to identify the one or more rail features in real-time; and
for the first image of the plurality of images, the processor is configured to:
classify a first set of one or more ojbects in the first image as one of the one or more rail features;
classify a second set of the one or more objects in the first image as extraneous features; and
filter out the extraneous features.

4. The rail vehicle of claim 1 , wherein the processor is configured to:
determine if one of the rail features is missing or displaced at a first rail plate; and
based on the determination that one of the rail features is missing or displaced at the first rail plate, generate an alert signal.

5. The rail vehicle of claim 4 , further comprising:
a work unit coupled to the frame and configured to perform one or more railroad maintenance or operation functions; and
wherein based on the alert signal, the processor is configured to control the work unit to perform a maintenance function at the first rail plate.

6. The rail vehicle of claim 1 , further comprising:
a second camera;
a third light source; and
a fourth light source; and
wherein:
the frame includes a second bracket assembly;
the third light source and fourth light source disposed on the second bracket assembly such that light emitted from the third and fourth light source is directed to opposing sides of a second rail of the rail track; and
the second camera is disposed between the third light source and the fourth light source and configured to take images of the second rail.

7. A railroad track feature detection system comprising:
an imaging device configured to be coupled to a frame of a rail vehicle and positioned such that the imaging device is configured to capture a plurality of images of a rail track as the rail vehicle moves along the rail track; and
a computer having:
at least one memory comprising instructions, at least a portion of the instructions configured as a neural network; and
at least one processor configured to execute the instructions, wherein the instructions cause the at least one processor to perform one or more operations in real-time;

wherein the one or more operations include:
receiving the plurality of images, and for each of the images:
assigning a location identifier; and
identifying one or more rail features that correspond to one of a plurality of predetermined rail features; and

determining a location of each of the one or more identified rail features;
assigning a first location identifier to a first image of the plurality of images,
identifying, in the first image, the one or more rail features;
assigning a second location identifier to a second image of the plurality of images,
comparing the first location identifier with the second location identifier to determine a first displacement distance between the identified rail features in the first image;
based on the first displacement distance, determining if one or more rail features in the second image correspond to one of the one or more identified rail features in the first image;
based on the determintion that:
a first subset of the one or more rail features in the second image correspond to at least one of the one or more identified rail features in the first image, setting the first subset as detected rail features and re-identifying the first subset of the one or more rail features; and
a second subset of the one or more rail features in the second image does not correspond to at least one of the one or more identified rail features in the first image, setting the second subset as detected rail features and identifying, in the first image, the second subset of the one or more rail features.

8. The system of claim 7 , further comprising:
assigning a third location identifier to a third image of the plurality of images,
comparing the third location identifier to the first and second location identifiers to determine a second displacement distance;
based on the second displacement distance, determining if the one or more rail features in the third image corresponds to one of the rail features of the first and second subsets; and
based on the determination that:
the first subset of the one or more rail features is not contained within the third image, setting the first subset of rail features as tracked rail features;
a third subset of the one or more rail features in the third image corresponds to at least one of the one or more identified rail features in the first image or the second image, re-identifying the third subset of the one or more rail features; and
a fourth subset of the one or more rail features in the third image does not correspond to at least one of the one or more identified rail features in the first and second images, identifying, in the third image, the fourth subset of the one or more rail features.

9. The system of claim 7 , wherein identifying one or more rail features includes identifying a rail plate, a hole defined by the rail plate, a colored marker disposed on a portion of the rail, an anchor, a work tie, and/or a joint bar.

10. The system of claim 7 , wherein the computer includes an object detector module, a color detector module, and a tracker mod

Assignees

• Harsco Technologies LLC

Inventors

• Fernandez Javier

Classifications

• G06T7/001 Primary

  using an image reference approach · CPC title

• B61C13/00

  Locomotives or motor railcars characterised by their application to special systems or purposes (B61C11/00 takes precedence; self-propelled scaffold cars, break-down cranes, inspection trolleys B61D15/00; general design of track recording vehicles B61K9/00) · CPC title

• B61C17/00

  Arrangement or disposition of parts; Details or accessories not otherwise provided for; Use of control gear and control systems · CPC title

• B61K9/08

  Measuring installations for surveying permanent way · CPC title

• G06T7/248

  involving reference images or patches · CPC title