Wildfire identification in imagery

Patent metadata

Field	Value
Publication number	US-12080137-B2
Application number	US-202117368256-A
Country	US
Kind code	B2
Filing date	Jul 6, 2021
Priority date	Jul 6, 2021
Publication date	Sep 3, 2024
Grant date	Sep 3, 2024

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying wildfire in satellite imagery. In some implementations, a server obtains a satellite image of a geographic region and a date corresponding to when the satellite image was generated. The server determines a number of pixels in the satellite image that are indicated as on fire. The server obtains satellite imagery of the geographic region from before the date. The server generates a statistical distribution from the satellite imagery. The server determines a likelihood that the satellite image illustrates fire based on a comparison of the determined number of pixels in the satellite image that are indicated as on fire to the generated statistical distribution. The server can compare the determined likelihood to a threshold. In response to comparing the determined likelihood to the threshold, the server provides an indication that the satellite image illustrates fire.

First claim

What is claimed is:

1. A computer-implemented method comprising:
obtaining, by a server, a satellite image of a geographic region and a date corresponding to when the satellite image was generated;
determining, by the server, a number of pixels in the obtained satellite image that are indicated as on fire;
obtaining, by the server, satellite imagery of the geographic region over a time period from before the date when the satellite image was generated;
generating, by the server, a statistical distribution over the time period from the obtained satellite imagery that reflects a number of pixels that each image of the obtained satellite imagery illustrates fire;
determining, by the server, a likelihood that the obtained satellite image illustrates fire based on a comparison of the determined number of pixels in the satellite image that are indicated as on fire to the generated statistical distribution;
comparing, by the server, the determined likelihood to a threshold;
determining, by the server, that the determined likelihood satisfies the threshold; and
in response to determining that the determined likelihood satisfies the threshold, providing, by the server, an indication that the obtained satellite image illustrates fire.

2. The computer-implemented method of claim 1 , wherein obtaining the satellite imagery of the geographic region from before the date when the satellite image was generated further comprises:
obtaining, by the server, a location that describes the geographic region;
providing, by the server and to a satellite images database, the location that describes the geographic region and the date corresponding to when the obtained satellite image was generated; and
in response to providing the location and the date to the satellite images database, obtaining, by the server, the satellite imagery that illustrates the geographic region from a time period prior to the date.

3. The computer-implemented method of claim 1 , wherein generating the statistical distribution over the time period from the satellite imagery further comprises:
selecting, by the server, a subset of satellite imagery from the obtained satellite imagery, wherein the selecting comprises:
identifying, by the server, the time period to generate the statistical distribution, the time period corresponding to a period prior to the date the satellite image was captured;
selecting, by the server, the subset of imagery from the obtained satellite imagery based on the time period;
determining, by the server, an indication if one or more pixels from the subset of satellite imagery illustrates fire; and
adjusting, by the server, the subset of satellite imagery by comparing the one or more pixels that illustrates fire to a threshold value if one or more satellite imagery of the subset illustrates fire.

4. The computer-implemented method of claim 3 , wherein generating the statistical distribution over the time period from the obtained satellite imagery further comprises:
in response to adjusting the subset of satellite imagery, generating, by the server, one or more parameters of the statistical distribution by:
determining, by the server, a number of pixels on each day of the subset of satellite imagery that illustrate fire;
determining, by the server, an average of the number of pixels on each day of the subset of satellite imagery that illustrate fire; and
generating, by the server, the statistical distribution by setting the determined average to the one or more parameters.

5. The computer-implemented method of claim 1 , wherein determining the number of pixels in the obtained satellite image that are indicated as on fire further comprises one or more of:
determining, by the server, the number of pixels in the obtained satellite image that are indicated as on fire based on a fire detection algorithm executing over one or more pixels within a bounding box cropped on the obtained satellite image; or
determining, by the server, the number of pixels within the bounding box in the obtained satellite image that are indicated as on fire based on comparing an intensity value for each pixel to a second threshold value; and
in response to determining a set number of pixels from the number of pixels within the bounding box are each greater than the second threshold value, identifying, by the server, the set number of pixels as pixels illustrating fire in the obtained satellite image.

6. The computer-implemented method of claim 5 , wherein determining the likelihood that the obtained satellite image illustrate fire based on the comparison of the determined number of pixels in the obtained satellite image that are indicated as on fire to the generated statistical distribution further comprises providing, by the server, data representing the set number of pixels as pixels illustrating the fire in the obtained satellite image as input to the generated statistical distribution.

7. The computer-implemented method of claim 1 , in response to comparing the determined likelihood to the threshold, determining, by the server, whether the obtained satellite image illustrates fire depending on a side of the threshold the likelihood lies.

8. The computer-implemented method of claim 1 , further comprising in response to the indication that the obtained satellite image illustrates fire, determining, by the server, that the determined likelihood is less than the threshold.

9. The computer-implemented method of claim 1 , wherein providing the indication that the obtained satellite image illustrates fire further comprises providing, by the server, the obtained satellite image and a corresponding indication that the obtained satellite image illustrates fire to a graphical user interface (GUI) on a display, the GUI illustrates multiple satellite images stitched together over various geographical regions with one or more indications of fire pixels in the multiple satellite images.

10. A system comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
obtaining, by a server, a satellite image of a geographic region and a date corresponding to when the satellite image was generated;
determining, by the server, a number of pixels in the obtained satellite image that are indicated as on fire;
obtaining, by the server, satellite imagery of the geographic region over a time period from before the date when the satellite image was generated;
generating, by the server, a statistical distribution over the time period from the obtained satellite imagery that reflects a number of pixels that each image of the obtained satellite imagery illustrates fire;
determining, by the server, a likelihood that the obtained satellite image illustrates fire based on a comparison of the determined number of pixels in the satellite image that are indicated as on fire to the generated statistical distribution;
comparing, by the server, the determined likelihood to a threshold;
determining, by the server, that the determined likelihood satisfies the threshold; and
in response to determining that the determined likelihood satisfies the threshold, providing, by the server, an indication that the obtained satellite image illustrates fire.

11. The system of claim 10 , wherein obtaining the satellite imagery of the geographic region from before the date when the satellite image was generated further comprises:
obtaining, by the server, a location that describes the geographic region;
providing, by the server and to a satellite images database, the location that describes the geographic region

Assignees

• X Dev Llc

Inventors

• Cowan Eliot Julien
• Cowan Avery Noam
• Gupta Akshina

Classifications

• G06T2210/12

  Bounding box · CPC title

• G06T2207/10032

  Satellite or aerial image; Remote sensing · CPC title

• G06T11/20

  Drawing from basic elements · CPC title

• G06F16/29

  Geographical information databases · CPC title

• G06T7/77

  using statistical methods · CPC title