Track feature detection using machine vision
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.
1. A railroad track feature detection system comprising:
a camera configured to capture a plurality of images,
one or more light sources; and
a computing system 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 operations comprising:
receiving a first image of the plurality of images;
detecting one or more imaged rail features in the first image;
identifying a first rail feature of the one or more imaged rail features;
determining location information of the first rail feature; and
sending one or more instructions based on the location information of the first rail feature to cause a maintenance action to be performed on the first rail feature.
2. The railroad track feature detection system of claim 1 , wherein the one or more instructions include instructions for a drone rail maintenance vehicle to repair the first rail feature.
3. The railroad track feature detection system of claim 1 , wherein the one or more instructions include instructions for a drone rail maintenance vehicle to inspect the first rail feature.
4. The railroad track feature detection system of claim 1 , wherein determining location information of the first rail feature includes global positioning system (GPS) coordinates.
5. The railroad track feature detection system of claim 1 , wherein the operations further comprise:
receiving a second image of the plurality of images;
detecting one or more second imaged rail features in the second image;
identifying a second rail feature of the one or more second imaged rail features;
determining location information of the second rail feature; and
sending one or more second instructions based on the location information of the second rail feature to cause an action to be performed on the second rail feature.
6. The railroad track feature detection system of claim 5 , wherein determining location information of the second rail feature includes measuring a distance between the first and second rail feature.
7. The railroad track feature detection system of claim 5 , wherein the first and second rail feature includes an anchor, a spike, a rail tie, a tie plate, or a rail joint.
8. The railroad track feature detection system of claim 1 , wherein the operations comprise storing feature identifiers and location information of the first and second rail features.
9. The railroad track feature detection system of claim 1 , wherein the camera and the one or more light sources are coupled to a frame of a rail vehicle and positioned such that the plurality of images include a rail track.
10. A non-transitory computer readable medium comprising instructions that, when executed by a processor, causes the processor to:
receive a plurality of images from a camera coupled to a frame of a rail vehicle, the camera positioned such that the plurality of images contain a rail track;
detect a plurality of imaged rail features in the plurality of images;
identify the detected rail features and assign feature identifiers to each of the identified rail features;
detect and identify a color marker in the plurality of images;
based on the color marker, determine a first rail feature of the plurality of imaged rail features in need of maintenance; and
based on the determination, generate an alert.
11. The non-transitory computer readable medium of claim 10 , wherein the instructions further cause the processor to generate instructions to repair the first rail feature.
12. The non-transitory computer readable medium of claim 11 , wherein the instructions further cause the processor to send the instructions to repair the first rail feature to a drone rail maintenance vehicle.
13. The non-transitory computer readable medium of claim 10 , wherein the feature identifiers include:
feature identification information that corresponds to one railroad track feature of a database of railroad track features; and
location information.
14. The non-transitory computer readable medium of claim 13 , wherein the instructions further cause the processor to:
measure a distance between the first rail feature and a second identified rail track feature; and
wherein:
the first rail feature is contained in a first image of the plurality of images; and
the second identified rail track feature is contained in a second image of the plurality of images.
15. The non-transitory computer readable medium of claim 13 , wherein the database of railroad track features includes an anchor, a spike, a rail tie, a tie plate, and a rail joint.
16. The non-transitory computer readable medium of claim 10 , wherein the instructions further cause the processor to:
assign color identifiers to the identified color markers;
determine if the color marker is associated with a maintenance color; and
based on the determination, generate the alert.
17. The non-transitory computer readable medium of claim 16 , wherein the color identifiers include:
color identification information that corresponds one railroad track features of a database of railroad track features; and
location information.
18. The non-transitory computer readable medium of claim 17 , wherein the instructions further cause the processor to:
measure a distance between a first color marker and a second color marker; and
wherein:
the first color marker is contained in a first image of the plurality of images; and
the second color marker is contained in a second image of the plurality of images.