Aerial imaging for insurance purposes

Patent metadata

Field	Value
Publication number	US-11568494-B1
Application number	US-202016933358-A
Country	US
Kind code	B1
Filing date	Jul 20, 2020
Priority date	Jul 17, 2015
Publication date	Jan 31, 2023
Grant date	Jan 31, 2023

Abstract

In a computer-implemented method, one or more digital aerial images of a property of a current or potential policyholder may be received. The digital aerial image(s) may be processed to determine one or more features of the property, including one or more features of a tree. A predicted location of roots of the tree is determined based upon the tree feature(s). The property feature(s) is/are analyzed to determine a risk of damage to a structure located on the property, by analyzing at least the predicted location of roots of the tree to determine a risk of damage to a foundation of the structure. Based at least in part on this risk, a risk output is generated that includes an indication of whether action should be taken to mitigate the risk of damage and/or whether insurance coverage should be offered, and/or includes a measure of the risk of damage.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving, by one or more processors, one or more digital aerial images of a property of a current or potential policyholder;
processing, by one or more processors, the one or more digital aerial images according to one or more image analysis techniques to determine one or more features of the property, wherein processing the one or more digital aerial images includes determining one or more features of a tree located on or near the property;
determining a predicted location of roots of the tree based upon the one or more features of the tree;
analyzing, by one or more processors, the one or more features of the property to determine a risk of damage to a structure located on the property, wherein analyzing the one or more features of the property includes analyzing at least the predicted location of roots of the tree to determine a risk of damage to a foundation of the structure; and
generating, by one or more processors and based at least in part on the risk of damage to the structure, a risk output that includes one or more of (i) an indication of whether action should be taken to mitigate the risk of damage to the structure, (ii) an indication of whether insurance coverage associated with the structure should be offered, or (iii) a measure of the risk of damage to the structure.

2. The computer-implemented method of claim 1 , wherein receiving the one or more digital aerial images includes receiving one or more digital aerial images obtained using at least one of (i) a sensor mounted on a satellite, (ii) a sensor mounted on an airplane, or (iii) a sensor mounted on a drone.

3. The computer-implemented method of claim 2 , wherein receiving the one or more digital aerial images includes receiving one or more digital aerial images obtained using at least one of (i) a camera, (ii) a spectrometer, (iii) a light detection and ranging (LiDAR) device, (iv) a semi-global matching (SGM) device, or (v) a Synthetic Aperture Radar Interferometry (IFSAR) device.

4. The computer-implemented method of claim 1 , wherein:
receiving the one or more digital aerial images includes receiving a plurality of digital aerial images (i) obtained using a camera and (ii) including at least two digital aerial images having different angles of incidence with respect to the property;
determining the one or more features of the tree includes (i) processing the at least two digital aerial images having the different angles of incidence to determine a height of the tree, and (ii) processing at least one of the plurality of digital aerial images to determine a distance between the tree and the structure; and
analyzing the one or more features of the property to determine the risk of damage to the structure includes analyzing the height of the tree and the distance between the tree and the structure to determine a risk of the tree falling on the structure.

5. The computer-implemented method of claim 1 , wherein:
receiving the one or more digital aerial images includes receiving a plurality of digital aerial images that includes a LiDAR, IFSAR or SGM image of the property;
determining the one or more features of the tree includes (i) processing the LiDAR, IFSAR or SGM image to determine a height of the tree, and (ii) processing at least one of the plurality of digital aerial images to determine a distance between the tree and the structure; and
analyzing the one or more features of the property to determine a risk of damage to the structure includes analyzing the height of the tree and the distance between the tree and the structure to determine a risk of the tree falling on the structure.

6. The computer-implemented method of claim 1 , wherein determining the one or more features of the tree includes determining an orientation of a branch of the tree with respect to the structure.

7. The computer-implemented method of claim 1 , wherein determining the one or more features of the tree includes determining a species of the tree.

8. The computer-implemented method of claim 7 , wherein:
determining the one or more features of the tree includes
determining one or both of a height of the tree and a crown width of the tree, and
using (i) the species of the tree, and (ii) one or both of the height of the tree and the crown width of the tree, to determine a stage of a life cycle of the tree; and

analyzing the one or more features of the property to determine a risk of damage to the structure includes analyzing at least the stage of the life cycle of the tree to determine the risk of at least a portion of the tree falling on the structure.

9. The computer-implemented method of claim 7 , wherein:
receiving the one or more digital aerial images includes receiving a spectrometer image obtained using a spectrometer; and
determining a species of the tree includes analyzing the spectrometer image to determine the species of the tree.

10. The computer-implemented method of claim 1 , wherein:
determining the one or more features of the tree includes determining one or more features of leaves on the tree;
the method further comprises determining a time of year corresponding to at least one of the one or more digital aerial images; and
analyzing the one or more features of the property to determine a risk of damage to the structure includes using (i) the one or more features of leaves on the tree, and (ii) the time of year, to determine the risk of damage to the structure.

11. The computer-implemented method of claim 1 , further comprising:
determining a type of a roof of the structure,
wherein analyzing the one or more features of the property to determine a risk of damage to the structure includes using (i) the one or more features of the tree, and (ii) the type of the roof, to determine the risk of damage to the roof.

12. The computer-implemented method of claim 1 , further comprising:
determining environmental stressor information with respect to an area that includes the property, the environmental stressor information including one or more of (i) whether the area is or has been subject to prolonged drought, (ii) whether the area has water-logged soil, (iii) whether the area is or has been subject to an ice storm, (iv) whether the area is or has been subject to a wildfire, or (v) whether the area is or has been subject to a tree disease or insect infestation,
wherein analyzing the one or more features of the property to determine a risk of damage to the structure includes using (i) the one or more features of the tree, and (ii) the environmental stressor information, to determine the risk of damage to the structure.

13. The computer-implemented method of claim 1 , further comprising:
determining weather forecast information with respect to an area that includes the property,
wherein analyzing the one or more features of the property to determine a risk of damage to the structure includes using (i) the one or more features of the property, and (ii) the weather forecast information, to determine the risk of damage to the structure.

14. The computer-implemented method of claim 1 , wherein processing the one or more digital aerial images to determine the one or more features of the property includes determining one or more features of a snow or ice formation located on a roof of a structure located on the property.

15. The computer-implemented method of claim 1 , further comprising:
determining whether the risk of damage to the structure exceeds one or both of (i) a threshold likelihood of damage, and (ii) a threshold predicted amount of damage,
wherein generating the r

Assignees

• State Farm Mutual Automobile Insurance Co

Inventors

• Davis Timothy Joel
• Engelhorn Amy
• Custer Tami R
• Przybylski Karen E
• Szews Paul C
• Grant Rosemarie Geier
• Haefli Eric
• Paulette Jr Arthur P

Classifications

• G06V20/188

  Vegetation · CPC title

• G06V20/176

  Urban or other man-made structures · CPC title

• G06T2207/30184

  Infrastructure · CPC title

• G06T2207/30188

  Vegetation; Agriculture · CPC title

• G06Q50/163 Primary

  Real estate management · CPC title