Wildfire defender

Patent metadata

Field	Value
Publication number	US-2022215744-A1
Application number	US-202217700652-A
Country	US
Kind code	A1
Filing date	Mar 22, 2022
Priority date	Sep 27, 2019
Publication date	Jul 7, 2022
Grant date	—

Abstract

A system includes a processing device and memory device storing instructions that result in accessing a first dataset including aerial imagery data and infrared data, accessing a second dataset including property boundary data, and identifying property boundaries associated with a geographic area. A plurality of models is applied to the datasets to identify and compute information of interest. Based on the first dataset and constrained by the property boundaries, a building detection model can be applied to identify a building, and a vegetation detection model can be applied to identify one or more areas of vegetation. An estimated distance can be determined between each of the areas of vegetation and the building as separation data, which can be compared to a defensible space guideline to determine a defensible space adherence score. A wildfire risk map can be generated, including the defensible space adherence score associated with the geographic area.

First claim

What is claimed is:

1 . A system, comprising:
a processing device; and a memory device in communication with the processing device, the memory device storing instructions that when executed by the processing device result in:
accessing a first dataset comprising aerial imagery data and infrared data associated with a geographic area;
accessing a second dataset comprising property boundary data associated with the geographic area;
identifying a plurality of property boundaries associated with the geographic area;
applying a building detection model to identify a building based on the first dataset and constrained by the property boundaries;
applying a vegetation detection model to identify one or more vegetation areas based on the first dataset and constrained by the property boundaries;
identifying a moisture content of the one or more vegetation areas based on the infrared data;
determining an estimated distance between each of the one or more vegetation areas and the building as separation data;
comparing the separation data to a defensible space guideline to determine a defensible space adherence score;
determining a fire risk adjustment based on the moisture content; and
generating a wildfire risk map comprising the defensible space adherence score associated with the geographic area, wherein the wildfire risk map incorporates the fire risk adjustment.

2 . The system of claim 1 , further comprising instructions that when executed by the processing device result in:
accessing a plurality of datasets from an archive comprising the aerial imagery data and the infrared data associated with the geographic area and collected over a period of time; determining the defensible space adherence score and the fire risk adjustment over the period of time based on the datasets from the archive; and identifying one or more areas of change with respect to landscape management for wildfire defense based on the defensible space adherence score and the fire risk adjustment over the period of time.

3 . The system of claim 2 , further comprising instructions that when executed by the processing device result in:
predicting a future fire risk of the geographic area or a neighboring geographic area based on identifying the one or more areas of change; and triggering an alert notification based on the future fire risk exceeding an alert threshold.

4 . The system of claim 1 , further comprising instructions that when executed by the processing device result in:
identifying one or more dead spots in the one or more vegetation areas based on the moisture content; and determining the fire risk adjustment based on a distance of the one or more dead spots to the building.

5 . The system of claim 1 , further comprising instructions that when executed by the processing device result in:
determining a condition of the building; and determining the fire risk adjustment based at least in part on the condition of the building.

6 . The system of claim 5 , wherein the condition of the building is determined based on identifying one or more of: a roof shape of the building, a chimney state of the building, and/or a roof vent of the building.

7 . The system of claim 5 , further comprising instructions that when executed by the processing device result in:
identifying a roofing material of the building based on the building detection model; detecting a roof condition comprising deterioration or damage to the roofing material; and determining the fire risk adjustment based at least in part on the roof condition.

8 . The system of claim 5 , wherein the condition of the building is determined based on one or more changes over time in the aerial imagery data of multiple datasets associated with the building.

9 . The system of claim 1 , wherein the condition of the building is associated with a deck of the building.

10 . The system of claim 1 , further comprising instructions that when executed by the processing device result in:
identifying one or more objects external to the building; and adjusting the wildfire risk map based on the one or more objects.

11 . The system of claim 10 , wherein the one or more objects comprise at least one fire hydrant or water source.

12 . The system of claim 10 , wherein the one or more objects comprise at least one fuel storage source.

13 . The system of claim 10 , wherein the one or more objects comprise at least one vehicle.

14 . The system of claim 1 , wherein the vegetation detection model comprises a three-dimensional model configured to characterize a vegetation size and classify a vegetation type.

15 . The system of claim 14 , wherein the vegetation type is classified as a species and the species maps to a wildfire risk with respect to the moisture content.

16 . The system of claim 1 , further comprising instructions that when executed by the processing device result in:
identifying a location of an electrical or gas utility connection at the building; and determining the defensible space adherence score based on a distance from the location to the one or more vegetation areas.

17 . A computer program product comprising a non-transitory storage medium embodied with computer program instructions that when executed by a computer cause the computer to implement:
accessing a first dataset comprising aerial imagery data and infrared data associated with a geographic area; accessing a second dataset comprising property boundary data associated with the geographic area; identifying a plurality of property boundaries associated with the geographic area; applying a building detection model to identify a building based on the first dataset and constrained by the property boundaries; applying a vegetation detection model to identify one or more vegetation areas based on the first dataset and constrained by the property boundaries; identifying a moisture content of the one or more vegetation areas based on the infrared data; determining an estimated distance between each of the one or more vegetation areas and the building as separation data; comparing the separation data to a defensible space guideline to determine a defensible space adherence score; determining a fire risk adjustment based on the moisture content; and generating a wildfire risk map comprising the defensible space adherence score associated with the geographic area, wherein the wildfire risk map incorporates the fire risk adjustment.

18 . The computer program product of claim 17 , further comprising computer program instructions that when executed by the computer cause the computer to implement:
accessing a plurality of datasets from an archive comprising the aerial imagery data and the infrared data associated with the geographic area and collected over a period of time; determining the defensible space adherence score and the fire risk adjustment over the period of time based on the datasets from the archive; and identifying one or more areas of change with respect to landscape management for wildfire defense based on the defensible space adherence score and the fire risk adjustment over the period of time.

19 . The computer program product of claim 18 , further comprising computer program instructions that when executed by the computer cause the computer to implement:
predicting a future fire risk of the geographic area or a neighboring geographic area based on identifying the one or more areas of change; and triggering an alert notification based on the future fire risk exc

Assignees

• Travelers Indemnity Co

Inventors

• Ton-That Hoa
• Dykstra James
• Han John
• Walker Stefanie M
• Amuso Joseph
• Lee George
• Kelsey Kyle J

Classifications

• G06F18/25

  Fusion techniques · CPC title

• G06T17/05

  Geographic models · CPC title

• G06V20/17

  taken from planes or by drones · CPC title

• G06V20/10

  Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) · CPC title

• G06V10/82

  using neural networks · CPC title