Thermal anomaly detection and classification

1. A system, comprising:

a processor configured to:

receive a set of images, wherein a first image included in the received set of images is associated with location information;

detect a thermal anomaly using the received set of images;

determine a classification for the detected thermal anomaly, using a set of criteria corresponding to a plurality of predetermined thermal anomaly types, wherein determining the classification includes determining whether the detected thermal anomaly is associated with a particular type of thermal anomaly included in a predetermined set of thermal anomaly types, at least in part by using the location information to determine whether the detected thermal anomaly is associated with a stationary target, and wherein at least one thermal anomaly type included in the predetermined set of thermal anomaly types includes a thermal anomaly that has a non-vegetation fuel source; and

in response to detecting an ignition event, take an action based at least in part on the classified detected thermal anomaly; and

a memory coupled to the processor and configured to provide the processor with instructions.

2. The system of claim 1 , wherein the received set of images comprises multi-spectral band data.

3. The system of claim 1 , wherein using the set of criteria includes determining that the detected thermal anomaly is not associated with a stationary target.

4. The system of claim 1 , wherein using the set of criteria includes determining that the detected thermal anomaly is not a gas flare.

5. The system of claim 1 , wherein using the set of criteria includes determining that the detected thermal anomaly is not associated with agriculture.

6. The system of claim 1 , wherein using the set of criteria includes determining that the detected thermal anomaly is not associated with a wildfire.

7. The system of claim 1 , wherein detecting the thermal anomaly includes applying a cloud mask.

8. The system of claim 7 , wherein the processor is further configured to generate the cloud mask.

9. The system of claim 1 , wherein the processor is further configured to generate a fire mask.

10. The system of claim 1 , wherein taking the action includes generating an ignition detection event.

11. The system of claim 1 , wherein detecting the thermal anomaly includes determining that the thermal anomaly is not associated with a previously generated ignition detection event.

12. A method, comprising:

receiving a set of images, wherein a first image included in the received set of images is associated with location information;

detecting a thermal anomaly using the received set of images;

determining a classification for the detected thermal anomaly, using a set of criteria corresponding to a plurality of predetermined thermal anomaly types, wherein determining the classification includes determining whether the detected thermal anomaly is associated with a particular type of thermal anomaly included in a predetermined set of thermal anomaly types, at least in part by using the location information to determine whether the detected thermal anomaly is associated with a stationary target, and wherein at least one thermal anomaly type included in the predetermined set of thermal anomaly types includes a thermal anomaly that has a non-vegetation fuel source; and

in response to detecting an ignition event, taking an action based at least in part on the classified detected thermal anomaly.

13. The method of claim 12 , wherein the received set of images comprises multi-spectral band data.

14. The method of claim 12 , wherein using the set of criteria includes determining that the detected thermal anomaly is not associated with a stationary target.

15. The method of claim 12 , wherein using the set of criteria includes determining that the detected thermal anomaly is not a gas flare.

16. The method of claim 12 , wherein using the set of criteria includes determining that the detected thermal anomaly is not associated with agriculture.

17. The method of claim 12 , wherein using the set of criteria includes determining that the detected thermal anomaly is not associated with a wildfire.

18. The method of claim 12 , wherein detecting the thermal anomaly includes applying a cloud mask.

19. The method of claim 12 , further comprising generating a fire mask.

20. The method of claim 12 , wherein taking the action includes generating an ignition detection event.

21. The method of claim 12 , wherein detecting the thermal anomaly includes determining that the thermal anomaly is not associated with a previously generated ignition detection event.

22. A non-transitory computer readable medium storing a computer program product comprising computer instructions for: receiving a set of images, wherein a first image included in the received set of images is associated with location information; detecting a thermal anomaly using the received set of images; determining a classification for the detected thermal anomaly, using a set of criteria corresponding to a plurality of predetermined thermal anomaly types, wherein determining the classification includes determining whether the detected thermal anomaly is associated with a particular type of thermal anomaly included in a predetermined set of thermal anomaly types, at least in part by using the location information to determine whether the detected thermal anomaly is associated with a stationary target, and wherein at least one thermal anomaly type included in the predetermined set of thermal anomaly types includes a thermal anomaly that has a non-vegetation fuel source; and in response to detecting an ignition event, taking an action based at least in part on the classified detected thermal anomaly.

23. The method of claim 18 , further comprising generating the cloud mask.