IP Library › Granted Patent US 12,662,176
Granted Patent B2
US 12,662,176 · App. 18/829,218 · Granted Jun 23, 2026

Apparatuses, systems, and methods for monitoring moving vehicles

Inventors: Mabby Nicholas Amouie (Atlanta, GA); Evan Thomas Gebhardt (Atlanta, GA); Colin Usher (Atlanta, GA); Benjamin Quick (Atlanta, GA); Trent Black (Atlanta, GA); Emily Strube (Atlanta, GA); Brian Thomas Yeager (Atlanta, GA); Thomas Samuel Fox (Atlanta, GA)
Assignee: Norfolk Southern Corporation & Georgia Tech Research Corporation
B61L25/021B61L25/025B61L25/04B61L27/53B61L27/57B61L27/70G01M17/10G06T7/0002G06T7/001G06T7/55G06T7/80G06V20/52G06V20/54G06V20/63G06V30/10H04N7/18H04N7/188H04N23/11H04N23/51H04N23/52H04N23/56H04N23/64H04N23/90G06T2207/10024G06T2207/10048G06T2207/30252G06V2201/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,662,176
App. No.
18/829,218
Granted
Jun 23, 2026
Kind
B2
Abstract

Railcar inspection systems, methods, and apparatuses are disclosed, including a railcar inspection portal. The railcar inspection portal includes a physical structure positioned around a railroad track, and through which a railcar can travel. The railcar inspection portal can include wheel detection sensors along the railroad track for detecting the presence of a railcar passing over the sensors. The sensors can transmit signals, corresponding to railcars passing over the sensors, to computing devices for determining railcar speeds. The railcar inspection portal can include imaging devices configured to capture images and readings of railcars passing through the inspection portal. Based on a determined speed corresponding to a passing railcar, the computing devices can control the imaging devices to capture specific areas or components of the passing railcar, or individual cars thereon. The computing devices can process the captured images to detect defects corresponding to the passing railcar, or individual cars thereon.

Claims (80)

1 . A system comprising:

one or more imaging devices configured to capture inspection images of a passing railcar travelling along a railway, the imaging devices comprises one or more infrared (IR) sensors;

one or more computing devices in communication with the one or more imaging devices, the one or more computing devices being configured to:

receive one or more IR images of one or more target regions of the passing railcar, each target region corresponding to one or more railcar components to be inspected;

process the one or more IR images to determine a detected heat pattern for a given target region of the one or more target regions by at least determining one or more determined shapes each corresponding to one or more temperature ranges;

determine that the detected heat pattern indicates that one or more components in the given target region has an operating temperature above a threshold temperature by at least:

comparing the one or more determined shapes of the detected heat pattern to one or more stored shapes of one or more stored heat patterns, the one or more stored heat patterns indicating an acceptable operating temperature for each of the one or more components in the given target region; and

determining that at least some of the one or more determined shapes is within a predetermined level of similarity to at least one of the one or more stored heat patterns;

in response to determining the one or more components in the given target region has an operating temperature above the threshold temperature, determine an abnormality associated with the detected heat pattern;

determine a likely root cause of the abnormality; and

output a notification comprising an identifier identifying the passing railcar, an indication of the abnormality, and an indication of the likely root cause.

2 . The system of claim 1 , wherein processing the one or more IR images comprises:

analyzing one or more pixel values for each pixel of each of the one or more IR images;

storing the one or more pixel values for each pixel of each of the one or more IR images in a vector format as a corresponding pixel vector of a plurality of pixel vectors for each of the one or more IR images; and

identifying, based at least in part on the plurality of pixel vectors for each of the one or more IR images, the detected heat pattern for the given target region.

3 . The system of claim 2 , wherein the one or more pixel values comprise RGB values.

4 . The system of claim 3 , wherein:

each component in the given target region has a range of acceptable operating temperatures; and

one or more groups pixels having RGB values indicating a temperature above the range of acceptable operating temperatures is indicative of the abnormality.

5 . A system comprising:

one or more imaging devices configured to capture inspection images of a passing railcar travelling along a railway, the imaging devices comprises one or more infrared (IR) sensors;

one or more computing devices in communication with the one or more imaging devices, the one or more computing devices being configured to:

receive one or more IR images of one or more target regions of the passing railcar, each target region corresponding to one or more railcar components to be inspected;

process the one or more IR images to determine a detected heat pattern for a given target region of the one or more target regions by at least determining one or more determined shapes each corresponding to one or more temperature ranges;

determine that the detected heat pattern indicates that one or more components in the given target region has an operating temperature above a threshold temperature by at least:

comparing the one or more determined shapes of the detected heat pattern to one or more stored shapes of one or more stored heat patterns, the one or more stored heat patterns indicating an unacceptable operating temperature for each of the one or more components in the given target region; and

determining that at least some of the one or more determined shapes is different from the one or more stored heat patterns;

in response to determining the one or more components in the given target region has an operating temperature above the threshold temperature, determine an abnormality associated with the detected heat pattern;

determine a likely root cause of the abnormality; and

output a notification comprising an identifier identifying the passing railcar, an indication of the abnormality, and an indication of the likely root cause.

6 . A method comprising:

capturing one or more infrared (IR) images of one or more target regions of a passing railcar travelling along a railway, each target region corresponding to one or more railcar components of the passing railcar;

processing the one or more IR images to determine a detected heat pattern for a given target region of the one or more target regions, wherein processing the one or more IR images comprises:

analyzing one or more pixel values for each pixel of each of the one or more IR images;

storing the one or more pixel values for each pixel of each of the one or more IR images in a vector format as a corresponding pixel vector of a plurality of pixel vectors for each of the one or more IR images; and

identifying, based at least in part on the plurality of pixel vectors for each of the one or more IR images, the detected heat pattern for the given target region by at least determining one or more determined shapes each corresponding to one or more temperature ranges;

determining that the detected heat pattern indicates that one or more components in the given target region has an operating temperature above a threshold temperature by at least:

comparing the one or more determined shapes of the detected heat pattern to one or more stored shapes of one or more stored heat patterns, the one or more stored heat patterns indicating an acceptable operating temperature for each of the one or more components in the given target region; and

determining that at least some of the one or more determined shapes is within a predetermined level of similarity to at least one of the one or more stored heat patterns;

in response to determining the one or more components in the given target region has an operating temperature above the threshold temperature, determining an abnormality associated with the detected heat pattern; and

outputting a notification comprising an identifier identifying the passing railcar and an indication of the abnormality.

7 . The method of claim 6 , further comprising determining a likely root cause of the abnormality, wherein the notification further comprises an indication of the likely root cause.

8 . The method of claim 6 , wherein processing the one or more IR images comprises:

analyzing one or more pixel values for each pixel of each of the one or more IR images;

storing the one or more pixel values for each pixel of each of the one or more IR images in a vector format as a corresponding pixel vector of a plurality of pixel vector for each of the one or more IR images; and

identifying, based at least in part on the plurality of pixel vector for each of the one or more IR images, the detected heat pattern for the given target region.

9 . A method comprising:

capturing one or more infrared (IR) images of one or more target regions of a passing railcar travelling along a railway, each target region corresponding to one or more railcar components of the passing railcar;

processing the one or more IR images to determine a detected heat pattern for a given target region of the one or more target regions, wherein processing the one or more IR images comprises:

analyzing one or more pixel values for each pixel of each of the one or more IR images;

storing the one or more pixel values for each pixel of each of the one or more IR images in a vector format as a corresponding pixel vector of a plurality of pixel vectors for each of the one or more IR images; and

identifying, based at least in part on the plurality of pixel vectors for each of the one or more IR images, the detected heat pattern for the given target region by at least determining one or more determined shapes each corresponding to one or more temperature ranges;

determining the detected heat pattern indicates that one or more components in the given target region has an operating temperature above a threshold temperature by at least:

comparing the one or more determined shapes of the detected heat pattern to one or more stored shapes of one or more stored heat patterns, the one or more stored heat patterns indicating an unacceptable operating temperature for each of the one or more components in the given target region; and

determining that at least some of the one or more determined shapes is within a predetermined level of similarity from the one or more stored heat patterns;

in response to determining the one or more components in the given target region has an operating temperature above the threshold temperature, determining an abnormality associated with the detected heat pattern; and

outputting a notification comprising an identifier identifying the passing railcar and an indication of the abnormality.

10 . A non-transitory, computer readable medium storing instructions that, when executed by one or processors, causes a computing system to:

output instructions to capture one or more infrared (IR) images of one or more target regions of a passing railcar travelling along a railway, each target region corresponding to one or more railcar components of the passing railcar;

process the one or more IR images to determine a detected heat pattern for a given target region of the one or more target regions, wherein processing the one or more IR images comprises:

analyzing one or more pixel values for each pixel of each of the one or more IR images;

storing the one or more pixel values for each pixel of each of the one or more IR images in a vector format as a corresponding pixel vector of a plurality of pixel vectors for each of the one or more IR images; and

identifying, based at least in part on the plurality of pixel vectors for each of the one or more IR images, the detected heat pattern for the given target region by at least determining one or more determined shapes each corresponding to one or more temperature ranges;

determine that the detected heat pattern indicates that one or more components in the given target region has an operating temperature above a threshold temperature by at least:

comparing the one or more determined shapes of the detected heat pattern to one or more stored shapes of one or more stored heat patterns, the one or more stored heat patterns indicating an acceptable operating temperature for each of the one or more components in the given target region; and

determining that at least some of the one or more determined shapes is within a predetermined level of similarity to at least one of the one or more stored heat patterns;

in response to determining the one or more components in the given target region has an operating temperature above the threshold temperature, determine an abnormality associated with the detected heat pattern; and

output a notification comprising an identifier identifying the passing railcar and an indication of the abnormality.

11 . A non-transitory, computer readable medium storing instructions that, when executed by one or processors, causes a computing system to:

output instructions to capture one or more infrared (IR) images of one or more target regions of a passing railcar travelling along a railway, each target region corresponding to one or more railcar components of the passing railcar;

process the one or more IR images to determine a detected heat pattern for a given target region of the one or more target regions, wherein processing the one or more IR images comprises:

analyzing one or more pixel values for each pixel of each of the one or more IR images;

storing the one or more pixel values for each pixel of each of the one or more IR images in a vector format as a corresponding pixel vector of a plurality of pixel vectors for each of the one or more IR images; and

identifying, based at least in part on the plurality of pixel vectors for each of the one or more IR images, the detected heat pattern for the given target region by at least determining one or more determined shapes each corresponding to one or more temperature ranges;

determine that the detected heat pattern indicates that one or more components in the given target region has an operating temperature above a threshold temperature by at least:

comparing the one or more determined shapes of the detected heat pattern to one or more stored shapes of one or more stored heat patterns, the one or more stored heat patterns indicating an unacceptable operating temperature for each of the one or more components in the given target region; and

determining that at least some of the one or more determined shapes is different from the one or more stored heat patterns;

in response to determining the one or more components in the given target region has an operating temperature above the threshold temperature, determine an abnormality associated with the detected heat pattern;

determine a likely root cause of the abnormality; and

output a notification comprising an identifier identifying the passing railcar, an indication of the abnormality, and an indication of the likely root cause.