Mask for satellite image data

Patent metadata

Field	Value
Publication number	US-12198347-B2
Application number	US-202217575406-A
Country	US
Kind code	B2
Filing date	Jan 13, 2022
Priority date	Jan 13, 2022
Publication date	Jan 14, 2025
Grant date	Jan 14, 2025

Abstract

A computing device is provided, including a processor configured to receive imaging relevance data for a geographic area. The processor may be further configured to generate, based at least in part on the imaging relevance data, image mask instructions specifying a region of interest included in the geographic area. The processor may be further configured to transmit the image mask instructions to a satellite. The processor may be further configured to receive, from the satellite, filtered satellite image data of the region of interest. One or more deprioritized regions of the geographic area outside the region of interest may be excluded from the filtered satellite image data.

First claim

The invention claimed is:

1. A computing device comprising:
a processor configured to:
receive imaging relevance data for a geographic area, wherein the imaging relevance data is received at least in part as sensor data from one or more external sensors configured to communicate with the computing device;
generate, based at least in part on the imaging relevance data, image mask instructions specifying a region of interest included in the geographic area, wherein:
the image mask instructions indicate a first priority level and a second priority level for a first subregion and a second subregion of the region of interest, respectively; and
the processor is configured to generate the image mask instructions at least in part by:
estimating a probability distribution that includes a plurality of probabilities that satellite image data associated with respective locations within the geographic area is relevant for a user-specified application of the satellite image data; and
assigning the first priority level to the first subregion and the second priority level to the second subregion based at least in part on whether the probabilities associated within the locations, as indicated by the probability distribution, are above or below a predetermined probability threshold;

transmit the image mask instructions to a satellite; and
receive, from the satellite, filtered satellite image data of the region of interest, wherein one or more deprioritized regions of the geographic area outside the region of interest are excluded from the filtered satellite image data.

2. The computing device of claim 1 , wherein:
the imaging relevance data includes meteorological data; and
the region of interest is a region of the geographic area that is not covered by clouds, as indicated by the meteorological data.

3. The computing device of claim 1 , wherein:
the filtered satellite image data includes first image data of the first subregion and second image data of the second subregion that differ in resolution.

4. The computing device of claim 1 , wherein the processor is configured to generate the image mask instructions at least in part by executing a machine learning model configured to receive the imaging relevance data as input.

5. The computing device of claim 4 , wherein the processor is further configured to train the machine learning model using training data that includes a plurality of training imaging relevance inputs paired with a respective plurality of training image mask instructions.

6. The computing device of claim 1 , wherein the imaging relevance data includes additional satellite image data received from the satellite or an additional satellite.

7. The computing device of claim 6 , wherein the region of interest is a region of the geographic area not depicted in the additional satellite image data.

8. The computing device of claim 1 , wherein:
the imaging relevance data includes vehicle tracking data for one or more vehicles;
the processor is further configured to compute one or more predicted locations of the one or more vehicles; and
the region of interest includes the one or more predicted locations.

9. The computing device of claim 1 , wherein the imaging relevance data includes seismographic data.

10. The computing device of claim 1 , wherein the imaging relevance data includes an estimated location of a fire boundary.

11. A method for use with a computing device, the method comprising:
receiving imaging relevance data for a geographic area, wherein the imaging relevance data is received at least in part as sensor data from one or more external sensors configured to communicate with the computing device;
generating, based at least in part on the imaging relevance data, image mask instructions specifying a region of interest included in the geographic area, wherein:
the image mask instructions indicate a first priority level and a second priority level for a first subregion and a second subregion of the region of interest, respectively; and
the method further comprises generating the image mask instructions at least in part by:
estimating a probability distribution that includes a plurality of probabilities that satellite image data associated with respective locations within the geographic area is relevant for a user-specified application of the satellite image data; and
assigning the first priority level to the first subregion and the second priority level to the second subregion based at least in part on whether the probabilities associated within the locations, as indicated by the probability distribution, are above or below a predetermined probability threshold;

transmitting the image mask instructions to a satellite; and
receiving, from the satellite, filtered satellite image data of the region of interest, wherein one or more deprioritized regions of the geographic area outside the region of interest are excluded from the filtered satellite image data.

12. The method of claim 11 , wherein:
the imaging relevance data includes meteorological data; and
the region of interest is a region of the geographic area that is not covered by clouds, as indicated by the meteorological data.

13. The method of claim 11 , wherein
the filtered satellite image data includes first image data of the first subregion and second image data of the second subregion that differ in resolution.

14. The method of claim 11 , wherein generating the image mask instructions includes executing a machine learning model configured to receive the imaging relevance data as input.

15. The method of claim 11 , wherein the imaging relevance data includes additional satellite image data received from the satellite or an additional satellite.

16. The method of claim 15 , wherein the region of interest is a region of the geographic area not depicted in the additional satellite image data.

17. The method of claim 11 , wherein:
the imaging relevance data includes vehicle tracking data for one or more vehicles;
the method further comprises computing one or more predicted locations of the one or more vehicles; and
the region of interest includes the one or more predicted locations.

18. A computing device comprising:
a processor configured to:
receive imaging relevance data for a geographic area, wherein the imaging relevance data includes:
meteorological data;
additional satellite image data received from a satellite or another satellite;
vehicle tracking data for one or more vehicles;
radar data;
LIDAR data;
seismographic data; and/or
an estimated location of a fire boundary;

generate, based at least in part on the imaging relevance data, image mask instructions specifying a region of interest included in the geographic area, wherein:
the image mask instructions indicate a first priority level and a second priority level for a first subregion and a second subregion of the region of interest, respectively; and
the processor is configured to generate the image mask instructions at least in part by:
estimating a probability distribution that includes a plurality of probabilities that satellite image data associated with respective locations within the geographic area is relevant for a user-specified application of the satellite image data; and
assigning the first priority level to the first subregion and the second priority level to the second subregion based at least in part on whether the probabilities associated within the locations, as indicated by the probability distribution, are above or below a predetermined probability threshold;

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Abdollahian Noghabi Shadi
• Chandra Ranveer
• Chintalapudi Krishna Kant
• Olsen Peder Andreas

Classifications

• G06V20/13 Primary

  Satellite images · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• G06T2207/30192

  Weather; Meteorology · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/20076

  Probabilistic image processing · CPC title