# US 2026/0094434 A1 · Image analysis systems and methods for wildfire risk assessment

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

- Number: US 2026/0094434 A1
- Document ID: US20260094434A1
- Status: Published application
- Kind: A1
- Application number: 19/413,010
- Filed: 2025-12-09
- Published: 2026-04-02
- Earliest claimed: 2023-08-29
- Assignees: Nearmap US, Inc.
- Applicants: Nearmap US, Inc.
- Inventors: Julius SIMONELLI; llsoo SEONG
- Web page: https://patentgrep.com/patent/US20260094434A1

## CPC

- G06V 20/188: {Vegetation}
- A62C 3/0271: {Detection of area conflagration fires (fire alarms for forest fires G08B17/005)}
- G01S 17/86: Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
- G01S 17/89: for mapping or imaging
- G06V 10/24: Aligning, centring, orientation detection or correction of the image
- G06V 20/176: {Urban or other man-made structures}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- A62C: FIRE-FIGHTING (fire-extinguishing compositions, use of chemical substances in extinguishing fires A62D1/00; spraying, applying liquids or other fluent materials to surfaces in general B05; alarm arrangements G08B, e.g. fire alarms actuated by smoke or gases G08B17/10)
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES

## Abstract

Methods, non-transitory computer-readable media, and property analysis systems are disclosed that extract vegetation location information from overhead and LIDAR images associated with a geographic location. The images are aligned based on the extracted vegetation information. Models are applied to the aligned images based on vegetation height information extracted from the LIDAR images. A graph is then generated based on a result of the application of the models. The graph represents a relationship between vegetation, one or more buildings, and one or more fire pathways associated with the geographic location. A wildfire risk score generated based on the graph is then output for the buildings via a GUI. Thus, the disclosed technology applies wildfire spread models and graphs to vegetation and buildings identified in aligned overhead and LIDAR imagery to provide relatively accurate wildfire risk assessment to insurers and homeowners and thereby facilitate informed decision-making and preventative measures.

## Claims

### Claim 1

A method implemented by a computer including a property analysis module executing on the computer, the method comprising the steps of:
receiving a wildfire risk request comprising a geographic location;
extracting data relating to vegetation from an image and a light detection and ranging (LIDAR) image associated with the geographic location;
aligning the vegetation image data and vegetation LIDAR data;
applying a model to the aligned data based at least in part on vegetation height data;
generating a graph that represents a relationship between vegetation, a building, and a fire pathway associated with the geographic location; and
outputting a wildfire risk score for the building in response to the wildfire risk request.

### Claim 2 (depends on 1)

The method of claim 1, wherein the model comprises an ember transport model and the method further comprises the steps of:
applying the ember transport model based on:
wind speed, or
relative positions of the vegetation; and
generating an indication of ember behavior during a wildfire event.

### Claim 3 (depends on 1)

The method of claim 1, wherein the model comprises a direct fire spread model and the method further comprises the step of:
applying the direct fire spread model to generate a likelihood of fire spread through contact between one or more of the vegetation and the building or between clusters of the vegetation.

### Claim 4 (depends on 3)

The method of claim 3, wherein the direct fire spread model accounts for one or more of the relative positions of the vegetation or other relative positions of the vegetation and the building.

### Claim 5 (depends on 1)

The method of claim 1, further comprising the steps of:
determining a mitigation action;
generating a graphical representation of the geographic location including at least one hazard or a relative wildfire risk associated with a region of the geographic location; and
outputting the mitigation action associated with the region.

### Claim 6 (depends on 1)

The method of claim 1, wherein the step of aligning the vegetation image data and vegetation LIDAR data includes combining the vegetation image data and the vegetation LIDAR data.

### Claim 7 (depends on 1)

The method of claim 1, wherein the vegetation height data is extracted from the LIDAR image.

### Claim 8

A property analysis system, comprising a computer having a memory and coupled to a network, the computer including a graphic user interface and configured to:
receive a wildfire risk request comprising a geographic location;
extract data relating to vegetation from an image and a light detection and ranging (LIDAR) image associated with the geographic location;
align the vegetation image data and vegetation LIDAR data;
apply a model to the aligned data based at least in part on vegetation height data;
generate a graph that represents a relationship between vegetation, a building, and a fire pathway associated with the geographic location; and
output a wildfire risk score for the building in response to the wildfire risk request.

### Claim 9 (depends on 8)

The property analysis system of claim 8, wherein the computer is further configured to:
generate an indication of ember behavior during a wildfire with an ember transport model that based on:
wind speed, or
relative position of vegetation.

### Claim 10 (depends on 8)

The property analysis system of claim 8, wherein the computer is further configured to:
generate a likelihood of fire spread through contact between one or more of the vegetation and the building or between clusters of the vegetation with a direct fire spread model that is based on one or more relative positions of the vegetation and the building.

### Claim 11 (depends on 10)

The property analysis system of claim 10, wherein the direct fire spread model accounts for one or more of the relative positions of the vegetation or other relative positions of the vegetation and the building.

### Claim 12 (depends on 8)

The property analysis system of claim 8, wherein the computer is further configured to:
determine one or more mitigation actions to reduce a wildfire risk for the geographic location;
generate a graphical representation of the geographic location including an indication of one or more potential hazards associated with the geographic location or a relative wildfire risk associated with one or more regions of the geographic location; and
output the graphical representation and the mitigation actions.

### Claim 13 (depends on 8)

The property analysis system of claim 8, wherein aligning the vegetation image data and vegetation LIDAR data includes combining the vegetation image data and the vegetation LIDAR data.

### Claim 14 (depends on 8)

The property analysis system of claim 8, wherein the vegetation height data is extracted from the LIDAR image.
