Granted Patent B2

US 12,667,739 · App. 17/863,298 · Granted Jun 30, 2026

Inventors: John Wall (Frankford, DE); Michael O'Dell (Alameda, CA)

A62C3/0278G06F30/13G06V20/176G06V20/188G06F2119/08

Abstract

Claims (130)

1 . A method comprising:

receiving at least one image of a property, wherein the property comprises at least one primary structure;

identifying structural features of the at least one primary structure by:

determining an inventory of exterior features of each at least one primary structure on the property, wherein the exterior features are located along a perimeter of the at least one primary structure and include dimensions and material composition;

utilizing a machine learning feature detection algorithm on each of the at least one image to characterize primary structural features necessary to model fire susceptibility;

determining at least one non-primary structure fuel source on the property and surrounding the property by:

utilizing a machine learning fuel load algorithm for:

detecting major vegetation including at least one of a tree and a shrub;

detecting secondary structures including at least one of a shed and a fence;

detecting neighboring rooftops within a distance of the primary structure that would contribute to advancement of a wildfire; and

detecting at least one of a footprint of the primary structure, roof characteristics of the primary structure, and local topological features, wherein the local topological features include at least one of a slope, a road, a hydrant, and an arroyo;

determining a feature-specific attribute for each of the structural features of the at least one primary structure and for features of each of the at least one non-primary structure fuel sources; and

calculating a fuel load in terms of thermal energy generation potential utilizing the feature-specific attributes.

2 . The method of claim 1 , further comprising:

overlaying a multi-dimensional grid on the at least one image of the property,

wherein the grid comprises a plurality of tiles and divides the property into analysis points, each analysis point represented by one tile, and

wherein a centroid of the primary structure is centered on the grid;

encoding each tile within the grid with associated fuel element details and structural element details; and

encoding tiles within the grid with associated topographical data.

3 . The method of claim 2 , further comprising:

determining, when exposed to at least one fuel source, a thermal energy output and a probability of ignition failure for each of the structural features of the at least one primary structure and for each of the at least one non-primary structure fuel sources, utilizing a fire risk algorithm,

the fire risk algorithm including:

a plurality of threat vectors, comprising:

a heat flux for radiant impact threat vector;

a flame front contact for direct flame impingement threat vector;

an ember mass accumulation and size population for firebrand accumulation threat vector; and

an ember penetration probability computation threat vector,

wherein the probability of ignition failure for each of the plurality of threat vectors comprises utilizing the structural features of the at least one primary structure, the features for each of the at least one non-primary structure fuel sources, spatial relationships between the at least one primary structure and the at least one non-primary structure fuel sources, and the feature-specific attributes for each of the structural features of the at least one primary structure and features for each of the at least one non-primary structure fuel sources;

a direct evaluation routine to determine whether each structural feature of the at least one primary structure ignites under an influence of each of the plurality of threat vectors summed over all of a plurality of fuel sources with direct access to each structural feature of the at least one primary structure;

a line of sight evaluation routine to determine an impact of each of the plurality of fuel sources within a line of sight of each tile including a portion of the primary structure;

calculating an ignition failure determination for each structural feature at each tile including a portion of the primary structure, wherein the calculations include the impact of the plurality of fuel sources with direct access to the primary structure and the plurality of fuel sources within the line of sight of each tile including a portion of the primary structure; and

an evaluation routine to determine whether each feature of the at least one non-primary structure fuel source ignites under the influence of each of the plurality of threat vectors.

4 . The method of claim 3 , further comprising:

updating the fire risk algorithm by cataloguing for each tile with an ignition failure:

a location of the tile;

the at least one structural feature or each feature of the at least one non-primary structure fuel source that failed;

each of the plurality of threat vectors that caused each structural feature and each feature of the at least one non-primary structure fuel source to fail;

each individual fuel source contributing to each specific threat vector causing a feature failure;

wind direction during the feature failure; and

a failure surplus for each feature failure, wherein the failure surplus measures an extra heat flux the failed feature experienced over a non-failure or non-ignition state.

5 . The method of claim 3 , further comprising:

determining an influence of wind on each of the plurality of threat vectors including:

calculating an impact of each direction of wind from at least north, south, east, and west compass headings on each of the plurality of threat vectors for each tile including a portion of the primary structure; and

calculating the impact of a plurality of wind speeds on each of the plurality of threat vectors for each tile including a portion of the at least one primary structure.

6 . The method of claim 5 , further comprising:

determining an overall risk assessment for an entire property including:

compiling a list of each ignited structural feature of the at least one primary structure and each ignited feature of the at least one non-primary structure fuel source;

placing the list in a Failure Mode Effect Analysis (FMEA) framework;

quantifying a relative risk of each item in the list in a Risk Priority Number (RPN) based on ignition impact by the tile and energy overage;

calculating a cumulative risk score for each of the plurality of threat vectors by evaluating the ignition failures of the at least one primary structure and calculating the energy overage and failure mode by ignition failure;

calculating a risk score for the entire property based on threat vector energy contributions to each ignition failure;

generating a risk assessment report including risk scores for at least one of each ignited structural feature, each structural feature, each ignited feature of the at least one non-primary structure fuel source, each feature of the at least one non-primary structural fuel sources, and the risk score for the entire property.

7 . The method of claim 6 , further comprising:

associating a heat flux contribution from multiple fuel sources to at least one ignition failure point;

identifying multiple failures in a same structural feature of the primary structure, wherein the multiple failures are caused by the heat flux contribution from the multiple fuel sources;

augmenting the FMEA framework to reflect the multiple failures of the same structural feature of the primary structure due to the heat flux from multiple sources; and

prioritizing risks based on each of the multiple failures in the same structural feature.

8 . The method of claim 7 , further comprising:

determining a remediation solution for the at least one ignition failure point, including:

applying the prioritized risks to generate a remediation score for the FMEA framework, thereby providing an ability to address remediation solutions in a failure event;

incorporating risk prioritization into the FMEA framework, thereby utilizing multiple failure contributions; and

generating a remediation report comprising the at least one ignition failure point and including remediation solutions based on the remediation score, wherein the remediation solutions include at least one of hardening the primary structure to ignition and reducing fuel loads surrounding the primary structure.

9 . The method of claim 1 , wherein the image is obtained through at least one of oblique satellite imagery, aerial imagery, ground imagery, real estate multiple listing service databases, and images from an application on a mobile device.

10 . The method of claim 1 , wherein the machine learning feature detection algorithm characterizes structural features including at least one of a window, a door, a vent, and a soffit.

11 . A computing apparatus comprising:

a processor; and

a memory storing instructions that, when executed by the processor, configure the apparatus to:

receive at least one image of a property, wherein the property comprises at least one primary structure;

identify structural features of the at least one primary structure by:

determine an inventory of exterior features of each at least one primary structure on the property, wherein the exterior features are located along a perimeter of the at least one primary structure and include dimensions and material composition;

utilize a machine learning feature detection algorithm on each of the at least one image to characterize primary structural features necessary to model fire susceptibility;

determine at least one non-primary structure fuel source on the property and surrounding the property by:

utilize a machine learning fuel load algorithm for:

 detect major vegetation including at least one of a tree and a shrub;

 detect secondary structures including at least one of a shed and a fence;

 detect neighboring rooftops within a distance of the primary structure that would contribute to advancement of a wildfire; and

 detect at least one of a footprint of the primary structure, roof characteristics of the primary structure, and local topological features, wherein the local topological features include at least one of a slope, a road, a hydrant, and an arroyo;

determine a feature-specific attribute for each of the structural features of the at least one primary structure and for features of each of the at least one non-primary structure fuel sources; and

calculate a fuel load in terms of thermal energy generation potential utilizing the feature-specific attributes.

12 . The computing apparatus of claim 11 , wherein the instructions further configure the apparatus to:

overlay a multi-dimensional grid on the at least one image of the property,

wherein the grid comprises a plurality of tiles and divides the property into analysis points, each analysis point represented by one tile, and

wherein a centroid of the primary structure is centered on the grid;

encode each tile within the grid with associated fuel element details and structural element details; and

encode tiles within the grid with associated topographical data.

13 . The computing apparatus of claim 12 , wherein the instructions further configure the apparatus to:

determine, when exposed to at least one fuel source, a thermal energy output and a probability of ignition failure for each of the structural features of the at least one primary structure and for each of the at least one non-primary structure fuel sources, utilizing a fire risk algorithm,

the fire risk algorithm including:

a plurality of threat vectors, comprising:

a heat flux for radiant impact threat vector;

a flame front contact for direct flame impingement threat vector;

an ember mass accumulation and size population for firebrand accumulation threat vector; and

an ember penetration probability computation threat vector,

wherein the probability of ignition failure for each of the plurality of threat vectors comprises utilize the structural features of the at least one primary structure, the features for each of the at least one non-primary structure fuel sources, spatial relationships between the at least one primary structure and the at least one non-primary structure fuel sources, and the feature-specific attributes for each of the structural features of the at least one primary structure and features for each of the at least one non-primary structure fuel sources;

a direct evaluation routine to determine whether each structural feature of the at least one primary structure ignites under an influence of each of the plurality of threat vectors summed over all of a plurality of fuel sources with direct access to each structural feature of the at least one primary structure;

a line of sight evaluation routine to determine an impact of each of the plurality of fuel sources within a line of sight of each tile include a portion of the primary structure;

calculate an ignition failure determination for each structural feature at each tile including a portion of the primary structure, wherein the calculations include the impact of the plurality of fuel sources with direct access to the primary structure and the plurality of fuel sources within the line of sight of each tile including a portion of the primary structure; and

an evaluation routine to determine whether each feature of the at least one non-primary structure fuel source ignites under the influence of each of the plurality of threat vectors.

14 . The computing apparatus of claim 13 , wherein the instructions further configure the apparatus to:

update the fire risk algorithm by cataloguing for each tile with an ignition failure:

a location of the tile;

the at least one structural feature or each feature of the at least one non-primary structure fuel source that failed;

each of the plurality of threat vectors that caused each structural feature and each feature of the at least one non-primary structure fuel source to fail;

each individual fuel source contribute to each specific threat vector causing a feature failure;

wind direction during the feature failure; and

a failure surplus for each feature failure, wherein the failure surplus measures an extra heat flux the failed feature experienced over a non-failure or non-ignition state.

15 . The computing apparatus of claim 13 , wherein the instructions further configure the apparatus to:

determine an influence of wind on each of the plurality of threat vectors including:

calculate an impact of each direction of wind from at least north, south, east, and west compass headings on each of the plurality of threat vectors for each tile including a portion of the primary structure; and

calculate the impact of a plurality of wind speeds on each of the plurality of threat vectors for each tile including a portion of the at least one primary structure.

16 . The computing apparatus of claim 15 , wherein the instructions further configure the apparatus to:

determine an overall risk assessment for an entire property including:

compile a list of each ignited structural feature of the at least one primary structure and each ignited feature of the at least one non-primary structure fuel source;

place the list in a Failure Mode Effect Analysis (FMEA) framework;

quantify a relative risk of each item in the list in a Risk Priority Number (RPN) based on ignition impact by the tile and energy overage;

calculate a cumulative risk score for each of the plurality of threat vectors by evaluating the ignition failures of the at least one primary structure and calculating the energy overage and failure mode by ignition failure;

calculate a risk score for the entire property based on threat vector energy contributions to each ignition failure; and

generate an a risk assessment report including risk scores for at least one of each ignited structural feature, each structural feature, each ignited feature of the at least one non-primary structure fuel sources, each feature of the at least one non-primary structural fuel sources, and the risk score for the entire property.

17 . The computing apparatus of claim 16 , wherein the instructions further configure the apparatus to:

associate a heat flux contribution from multiple fuel sources to at least one ignition failure point;

identify multiple failures in a same structural feature of the primary structure, wherein the multiple failures are caused by the heat flux contribution from the multiple fuel sources;

augment the FMEA framework to reflect the multiple failures of the same structural feature of the primary structure due to the heat flux from multiple sources; and

prioritize risks based on each of the multiple failures in the same structural feature.

18 . The computing apparatus of claim 17 , wherein the instructions further configure the apparatus to:

determine a remediation solution for the at least one ignition failure point, including:

apply the prioritized risks to generate a remediation score for the FMEA framework, thereby providing an ability to address remediation solutions in a failure event;

incorporate risk prioritization into the FMEA framework, thereby utilizing multiple failure contributions; and

generate a remediation report comprising the at least one ignition failure point and including remediation solutions based on the remediation score, wherein the remediation solutions include at least one of hardening the primary structure to ignition and reducing fuel loads surrounding the primary structure.

19 . The computing apparatus of claim 11 , wherein the image is obtained through at least one of oblique satellite imagery, aerial imagery, ground imagery, real estate multiple listing service databases, and images from an application on a mobile device.

20 . The computing apparatus of claim 11 , wherein the machine learning feature detection algorithm characterizes structural features including at least one of a window, a door, a vent, and a soffit.

Assignments (2)

Continuity (2)

References Cited (81)