US 12,214,813 B2
Track feature detection using machine vision
Javier Fernandez, Columbia, SC (US)
Assigned to HARSCO TECHNOLOGIES LLC, Fairmont, MN (US)
Filed by HARSCO TECHNOLOGIES LLC, Fairmont, MN (US)
Filed on Oct. 5, 2022, as Appl. No. 17/938,077.
Application 17/938,077 is a continuation of application No. 16/948,883, filed on Oct. 5, 2020, granted, now 11,495,009.
Application 16/948,883 is a continuation of application No. 15/933,004, filed on Mar. 22, 2018, granted, now 10,796,192.
Claims priority of provisional application 62/475,722, filed on Mar. 23, 2017.
Prior Publication US 2023/0278605 A1, Sep. 7, 2023
Int. Cl. B61L 23/04 (2006.01); G06V 10/56 (2022.01); G06V 20/56 (2022.01); H04N 7/18 (2006.01)
CPC B61L 23/042 (2013.01) [B61L 23/045 (2013.01); G06V 10/56 (2022.01); G06V 20/56 (2022.01); H04N 7/18 (2013.01)] 18 Claims
OG exemplary drawing
 
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.