Track feature detection using machine vision

Patent metadata

Field	Value
Publication number	US-10796192-B2
Application number	US-201815933004-A
Country	US
Kind code	B2
Filing date	Mar 22, 2018
Priority date	Mar 23, 2017
Publication date	Oct 6, 2020
Grant date	Oct 6, 2020

Abstract

The present disclosure generally relates to automated detection of railroad track features. Images of a railroad track are captured and analyzed to identify track features such as anchors, spikes, rail ties, tie plates, and joints. Various image processing techniques are utilized to accurately distinguish between track features and other objects in the captured images. Track features identified in the images are assigned identifiers and locations and stored in a database so that a status and/or condition of the track features may be monitored for maintenance purposes.

First claim

What is claimed is:

1. A railroad track feature detection system comprising:
a camera;
at least one light source; and
a computing apparatus comprising:
at least one memory comprising instructions; and
at least one processing device configured to execute the instructions, wherein the instructions cause the at least one processing device to perform the operations comprising:
capturing, using the camera, an image of a railroad track, wherein the at least one light source is used to capture the image, the image being composed of pixels;
determining, using a graphical processing unit (GPU) comprised in the at least one processing device, at least one color value of each pixel comprised in the image;
identifying, using a visual recognition unit comprised in the at least one processing device, an object in the image based on the determined color values, wherein the at least one processing device is configured to measure a shadow to identify a railroad track feature; and
assigning, using a tagging unit comprised in the at least one processing device, an identifier associated with the railroad track feature and a location to the identified object in a database.

2. The railroad track feature detection system of claim 1 , wherein:
the railroad track feature is an anchor or a spike; and
the color value comprises a red-green-blue (RGB) value.

3. The railroad track feature detection system of claim 1 , wherein the operations further comprise:
assigning a first range of hue values to correspond to a first color;
assigning a second range of hue values to correspond to a second color; and
assigning a third range of hue values to correspond to a third color.

4. The railroad track feature detection system of claim 1 , wherein the at least one color value includes a hue/saturation/value (HSV) value or a red-green-blue (RGB) value.

5. The railroad track feature detection system of claim 1 , wherein:
the object comprises a color marker; and
the operations further comprise identifying a contour based on the determined color values of adjacent pixels being greater than a predetermined threshold.

6. The railroad track feature detection system of claim 1 , wherein the light source is operable to cast a shadow of the railroad track feature.

7. The railroad track feature detection system of claim 1 , wherein the at least one processing device is configured to measure a size or a length of the shadow and the railroad track feature is identified based on the measured shadow.

8. A method for detecting a railroad track feature, the method comprising:
capturing, using a camera and a light source, an image of a railroad track, the image being composed of pixels;
determining at least one color value of each pixel comprised in the image;
identifying multiple color ranges, each color range of the multiple color ranges including a corresponding range of color values that correspond to at least one respective color;
for at least one pixel, performing a comparison of the at least one color value of the pixel to the color values to at least one of the multiple color ranges;
identifying an object in the image based on the determined color values and the comparison;
measuring a shadow to identify a railroad track feature; and
assigning an identifier associated with the railroad track feature and a location to the identified object.

9. The method of claim 8 , further comprising positioning the light source at an angle to the camera.

10. The method of claim 9 , further comprising using the light source to cast the shadow of the railroad track feature and measuring a size or a length of the shadow.

11. The method of claim 8 , further comprising determining a confidence score of the object.

12. The method of claim 11 , further comprising:
detecting a color marker on the railroad track; and
assigning an identifier and a location to the color marker.

13. The method of claim 8 , further comprising:
assigning a first range of color values to correspond to a first color; and
comparing the at least one color value of each pixel to the first range of color values.

14. The method of claim 8 , further comprising identifying a contour of the railroad track.

15. The method of claim 8 , further comprising filtering unwanted objects in the captured image.

16. The method of claim 8 , further comprising determining a hue/saturation/value (HSV) value of each pixel.

17. A system for detecting features on a rail track, the system comprising:
a camera;
at least one light source;
a processor; and
a memory device coupled to the processor, the memory device comprising instructions that, when executed by the processor, cause the processor to:
illuminate, by the at least one light source, a portion of a railroad track;
capture, by the camera, an image of the illuminated portion of the railroad track, the image being composed of pixels;
detect one or more shadow portions in the image, the shadow portions corresponding to a shadow cast by a track feature;
measure the shadow portions; and
identify the track feature based on the measured shadow portions.

18. The system of claim 17 , wherein the processor is further configured to produce a negative image of the captured image.

19. The system of claim 17 , wherein the processor is further configured to:
determine at least one color value of each pixel comprised in the image;
identify an object in the image based on the determined color values; and
assign an identifier associated with the railroad track feature and a location to the identified object in a database.

20. The system of claim 17 , wherein the processor is further configured to:
measure a size or a length of the shadow portions; or
identify the track feature from a plurality of identifiable types of track features.

Assignees

• Harsco Technologies LLC

Inventors

• Fernandez Javier

Classifications

• G06V10/56

  relating to colour · CPC title

• B61L23/042 Primary

  Track changes detection · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• H04N7/18

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

• B61L23/045

  Rail wear · CPC title