# US 2025/0095359 A1 · Systems and methods to determine vegetation encroachment along a right-of-way

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0095359 A1
- Document ID: US20250095359A1
- Status: Published application
- Kind: A1
- Application number: 18/589,742
- Filed: 2024-02-28
- Published: 2025-03-20
- Earliest claimed: 2023-09-18
- Assignees: Marathon Petroleum Company LP
- Applicants: Marathon Petroleum Company LP
- Inventors: Luke R. Miller; Joshua J. Beard; Brittan Battles
- Web page: https://patentgrep.com/patent/US20250095359A1

## CPC

- G06T 7/50: Depth or shape recovery
- A01D 34/835: specially adapted for particular purposes
- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 17/05: Geographic models
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V 10/764: using classification, e.g. of video objects
- G06V 20/17: taken from planes or by drones
- G06V 20/188: {Vegetation}
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A01D: HARVESTING; MOWING
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Embodiments of systems and methods to determine vegetation migration encroachment along a right-of-way associated with an underground feature are disclosed. In an embodiment, the method may include capturing images of one or more sections of the right-of-way at a selected time period. The method may include georeferencing the images to correlate the images with a surface of a geographical location of the right-of-way. The method may include determining and clipping an area of interest for the images. The method may include tiling clipped images to a preselected size to define a plurality of tiled clipped images. The method may include determining a vegetation migration encroachment onto the right-of-way by application of the clipped images to the trained machine learning model. The method may include, in response to a determination that the vegetation migration encroachment exceeds a threshold, generating an indication of vegetation migration encroachment.

## Claims

### Claim 1

A method to determine vegetation migration encroachment along a pipeline right-of-way, the method comprising:
capturing images of one or more sections of the pipeline right-of-way during a selected time period;
georeferencing the images to correlate the images with a surface of a geographical location of the pipeline right-of-way;
determining an area of interest for the images based on one or more of the geographical location of the pipeline right-of-way or previously known areas of interest;
clipping the area of interest for the images to define clipped images based on a pipeline right-of-way buffer;
tiling clipped images to a preselected size to define a plurality of tiled clipped images based on selected sizes utilized by a trained machine learning model;
determining a vegetation migration encroachment onto the pipeline right-of-way by application of the clipped images to the trained machine learning model;
generating an image for each portion the right-of-way overlayed with (a) one or more probability indicators that indicate potential vegetation encroachment based on the vegetation migration encroachment determined by the trained machine learning model and (b) one or more features of the corresponding portion of the pipeline right-of-way; and
in response to a determination that the vegetation migration encroachment exceeds a threshold, generating an indication of vegetation migration encroachment.

### Claim 2 (depends on 1)

The method of claim 1, wherein application of the clipped images to the trained machine learning model provides the indication of vegetation migration encroachment via images with overlayed pre-defined classifications.

### Claim 3 (depends on 2)

The method of claim 2, wherein the overlayed pre-defined classification comprises one or more of the pipeline right-of-way, one or more types of vegetation, or other objects.

### Claim 4

(canceled)

### Claim 5 (depends on 1)

The method of claim 1, wherein the area of interest for the images comprises one or more areas based on one or more of (a) geographic location or (b) a risk associated with the one or more sections of the pipeline right-of-way.

### Claim 6 (depends on 1)

The method of claim 1, wherein training the trained machine learning model comprises:
collecting historical images of the one or more sections of the pipeline right-of-way,
classifying vegetation and portions of the pipeline right-of-way in the historical images to generate a classified set of historical images,
training a machine learning model with a first subset of the classified set of historical images to generate the trained machine learning model, and
testing the trained machine learning model with a second subset of the classified set of historical images.

### Claim 7 (depends on 6)

The method of claim 6, wherein testing the trained machine learning model produces a model accuracy value, and the method further comprising, in response to the model accuracy value being less than a selected threshold:
collecting additional images, and
re-training the trained machine learning model with the additional images.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
in response to reception of a marked up vegetation migration encroachment or a validated vegetation migration encroachment, refining the trained machine learning model with one or more of the marked up vegetation migration encroachment or the validated vegetation migration encroachment.

### Claim 9

(canceled)

### Claim 10 (depends on 7)

The method of claim 7, wherein the additional images include marked up images indicating a type of vegetation encroachment, and wherein the type of vegetation encroachment includes one or more of (a) vegetation growing on a surface of the pipeline right-of-way of a selected height or (b) canopy overgrowth along the pipeline right-of-way.

### Claim 11 (depends on 1)

The method of claim 1, wherein application of the clipped images to the trained machine learning model produces one or more of: (a) a location and size of vegetation encroachment, (b) spatial data of the pipeline right-of-way, (c) a three dimensional image including polygons indicating vegetation migration encroachment, (d) a two dimensional image including indicators for the vegetation encroachment, or (e) coordinates of vegetation encroachment.

### Claim 12 (depends on 1)

The method of claim 1, wherein the indication of vegetation migration encroachment includes an alert, wherein the alert includes a remedial or corrective action, and wherein the remedial or corrective action comprises one or more of (a) cutting branches or trees, (b) mowing a portion of the pipeline right-of-way, or (c) removing other objects blocking the pipeline right-of-way.

### Claim 13 (depends on 1)

The method of claim 1, wherein the pipeline right-of-way buffer comprises a range of about 20 feet to about 50 feet from a center of the pipeline right-of-way.

### Claim 14 (depends on 1)

The method of claim 1, wherein a controller stores the trained machine learning model, wherein the trained machine learning model utilizes a semantic segmentation algorithm, and wherein the trained machine learning model (a) determines, via the semantic segmentation algorithm, a category of each pixel in each of the clipped images and (b) determines the vegetation migration encroachment based on the category of each pixel in each of the clipped images.

### Claim 15

A method to determine vegetation migration encroachment along a right-of-way associated with an underground feature, the method comprising:
capturing images of one or more sections of the right-of-way that corresponds to the underground feature at during a selected time period;
pre-processing the images so as to define pre-processed images;
determining vegetation migration encroachment onto the right-of-way that corresponds to the underground feature by application of the pre-processed images to a trained machine learning model; and
in response to a determination that the vegetation migration encroachment exceeds a threshold, generating an image of the right-of-way with one or more probability indicators that indicate potential vegetation migration encroachment overlayed on the image of the right-of-way.

### Claim 16 (depends on 15)

The method of claim 15, wherein pre-processing the images comprises:
georeferencing the images to correlate the images with a surface of a geographical location of the right-of-way,
determining an area of interest for the images,
clipping the area of interest for the images to define clipped images, and
tiling clipped images to a preselected size so as to define the pre-processed images based on one or more selected sizes utilized by a trained machine learning model.

### Claim 17 (depends on 16)

The method of claim 16, wherein determination of the area of interest is based on one or more of the geographical location of the right-of-way or a previously known areas of interest.

### Claim 18 (depends on 16)

The method of claim 16, wherein the clipping of the area of interest for the images is based on a right-of-way buffer.

### Claim 19 (depends on 18)

The method of claim 18, wherein the right-of-way buffer comprises a range of about 20 to about 50 feet from a center of the right-of-way.

### Claim 20 (depends on 15)

The method of claim 15, wherein the underground feature comprises one of utility lines, sewage lines or tanks, septic lines or tanks, or tunnels.

### Claim 21 (depends on 15)

The method of claim 15, wherein the underground feature comprises pipeline, and wherein the pipeline transports hydrocarbons.

### Claim 22

A system for managing and determining vegetation encroachment along an underground pipeline right-of-way, the system comprising:
an image capture circuitry configured to:
receive images of one or more sections of the underground pipeline right-of-way; and
a vegetation encroachment modeling circuitry configured to:
pre-process the images based on one or more of (a) a geographic location for each of the images, (b) known areas of interest, or an underground pipeline right-of-way buffer,
apply pre-processed images to a trained machine learning model,
determine an output image for each location represented in the images including probability indicators to indicate potential vegetation encroachment and the underground pipeline right-of-way,
determine whether the vegetation encroachment in any output image exceeds a selected threshold, and
in response to the vegetation encroachment exceeding the selected threshold, generate an indication of vegetation migration encroachment, the indication of vegetation migration encroachment also including remedial action.

### Claim 23 (depends on 22)

The system of claim 22, wherein the images are captured and received during a selected time period based on one or more of a location or known inspection interval of one or more sections of the underground pipeline right-of-way.

### Claim 24 (depends on 23)

The system of claim 23, wherein the vegetation encroachment modeling circuitry further is configured to:
based on the output image for each of the one or more sections of the underground pipeline right-of-way, determine a new selected time period for each corresponding one or more sections of the underground pipeline right-of-way.

### Claim 25 (depends on 22)

The system of claim 22, further comprising one or more controllers, and wherein the one or more controllers include the image capture circuitry and the vegetation encroachment modeling circuitry.

### Claim 26

A computing device for determining vegetation encroachment along a pipeline right-of-way, the computing device comprising one or more processors and a non-transitory computer-readable storage medium storing software instructions that, when executed by the one or more processors:
in response to reception of images of one or more sections of the underground pipeline right-of-way from a selected time period, georeference the images to correlate the images with a surface of a geographical location of the underground pipeline right-of-way;
determine an area of interest for the images based on one or more of the geographical location of the pipeline right-of-way, previously known areas of interest, or corresponding selected inspection times;
clip the area of interest for the images to define clipped images based on an underground pipeline right-of-way buffer;
tile clipped images to a preselected size to define a plurality of tiled clipped images based on selected sizes utilized by a trained machine learning model;
determine vegetation migration encroachment onto the pipeline right-of-way by application of the clipped images to the trained machine learning model;
generate an image for the underground pipeline right-of-way overlayed with one or more features; and
in response to a determination that the vegetation migration encroachment exceeds a threshold;
generate an indication of vegetation migration encroachment, and
overlay probability indicators that indicate potential vegetation encroachment onto to the image for the underground pipeline right-of-way.

### Claim 27 (depends on 26)

The computing device of claim 26, wherein the images are high-resolution aerial images captured by a high-resolution camera on an unmanned aerial vehicle.

### Claim 28 (depends on 27)

The computing device of claim 27, wherein the georeferenced images are accurate within about 95% of actual landscape of the underground pipeline right-of-way, based on known landmarks and the high-resolution image camera positioned on the unmanned aerial vehicle.

### Claim 29 (depends on 26)

The computing device of claim 26, wherein the indication of vegetation migration encroachment includes images of the pipeline right-of-way overlayed with highlighted areas to indicate the vegetation migration encroachment.

### Claim 30 (depends on 26)

The computing device of claim 26, further comprising software instructions, when executed by the one or more processors, to, in response to generation of the indication of vegetation migration encroachment:
determine a level of the vegetation migration encroachment, and
if the level of the vegetation migration encroachment exceeds a threshold, generate an alert.

### Claim 31

(canceled)

### Claim 32 (depends on 22)

The system of claim 22, wherein the vegetation encroachment modeling circuitry controls one or more vehicles or components associated with one or more of the underground pipeline right-of-way or the underground pipeline, and wherein the vegetation encroachment modeling circuitry is further configured to one of perform or initiate the remedial action via the one or more vehicles or components.