SYSTEM FOR PLANETARY-SCALE ANALYTICS

• US 20170250751A1
• Filed: 02/28/2017
• Published: 08/31/2017
• Est. Priority Date: 02/29/2016
• Status: Active Grant

• Current Assignee: URUGUS S A
• Original Assignee: Satellogic Overseas, Inc. (BVI)
• Inventors: Kargieman, Emiliano, Richarte, Gerardo Gabriel
• Granted Patent: US 11,101,876 B2
• Time in Patent Office: Days
• CPC Class Codes: G01C 11/02 Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/26 Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
• CPC Class Codes: G06V 10/40 Extraction of image or video features
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 20/176 Urban or other man-made structures
• CPC Class Codes: G06V 20/188 Vegetation
• CPC Class Codes: G06V 20/194 using hyperspectral data, i.e. more or other wavelengths than RGB
• CPC Class Codes: H04B 7/18513 Transmission in a satellite or space-based system
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

A smart satellite system is capable of decision making and prioritization on the fly to optimize the use of downlink bandwidth to deliver prioritized data based upon opportunity and the resources of available payloads. By providing a satellite system with substantial processing power and a level of autonomy, the satellite is able to make decisions about capturing imagery data, including image data processing, object detection, image segmentation, and re-orientation of the satellite based upon the opportunity, from the satellite'"'"'s perspective, for capturing image data of areas or objects of interest. Through the use of machine learning and in-orbit image analysis, the satellite may transmit only a subset of the captured images, portions of the captured images, or the result of image analysis, thereby efficiently using the downlink communication channel.

Claims

1. An orbital satellite system, comprising:

one or more sensors;

one or more processors;

memory coupled to the one or more processors, the memory including one or more modules that are executable by the processors to;

receive, from a ground-based device, a request for data, the request for data including a request to determine one or more parameters relating to at least one object within a particular geographic region;

capture, by a first sensor of the one or more sensors, one or more images associated with the particular geographic region;

determine that a first subset of images of the one or more images provides an unobstructed view of the particular geographic region;

capture, based at least in part upon the first subset of images providing an unobstructed view, a second set of images, the second set of images captured by a second sensor having a higher resolution that the first sensor;

determine that the second set of images includes data associated with the at least one object;

determine the one or more parameters associated with the request for data, based at least in part on the second set of images; and

transmit, to the ground-based device, the one or more parameters.

2. The orbital satellite system as in claim 1, wherein the one or more parameters comprises counting objects within the particular geographic region.

3. The orbital satellite system as in claim 1, wherein determine that a first subset of images of the one or more images provides an unobstructed view of the particular geographic region comprises analyzing the one or more images using a cloud-detection algorithm to identify areas of the image that are unobstructed by clouds.

4. The orbital satellite system as in claim 1, wherein the request for data includes a set of instructions provided to the orbital satellite system that are to be executed when the satellite system determines that one or more conditions are satisfied.

5. The orbital satellite system as in claim 4, wherein the one or more conditions include current time and date, a location, position, orientation, available payloads, available energy, or current temperature of the orbital satellite system.

6. A satellite system, comprising:

one or more processors;

an imaging system; and

one or more memories coupled to the one or more processors, the one or more memories including instructions, that when executed by the one or more processors, cause the one or more processors to perform acts comprising;

capturing, by a first imaging sensor of the imaging system, one or more first images;

analyzing the one or more first images to identify a feature of interest;

determining, based upon the feature of interest, a second set of instructions to be executed by the one or more processors;

capturing, based upon the second set of instructions, one or more second images;

analyzing the one or more second images to generate an analysis; and

transmitting the analysis to a ground station.

7. The satellite system as in claim 6, wherein analyzing the one or more first images includes executing a cloud-detection algorithm to determine areas of the one or more first images in which a view of earth is unobstructed by clouds.

8. The satellite system as in claim 6, wherein analyzing the one or more first images includes executing an object detection algorithm to detect objects on a surface of earth.

9. The satellite system as in claim 8, wherein the acts further comprise segmenting the one or more second images into subimages such that at least a first subimage contains the feature of interest.

10. The satellite system as in claim 8, wherein the analyzing the one or more second images includes determining a number of instances of a semantic object of a predetermined class.

11. The satellite system as in claim 6, wherein the second set of instructions include repositioning the satellite system.

12. The satellite system as in claim 6, wherein the second set of instructions includes changing a priority of instructions the satellite system is tasked to perform.

13. The satellite system as in claim 6, wherein the one or more memories store a list of tasks for the satellite system to complete, and the acts further comprise generating, based at least in part upon the one or more first images, a new task for the satellite to complete.

14. The satellite system as in claim 6, wherein the one or more first images is analyzed by executing artificial intelligence or machine learning algorithms on board.

15. The satellite system as in claim 6, wherein the one or more first images is analyzed by executing instructions received from a ground-station or from another satellite.

16. A method under control of one or more processors in an orbiting satellite, the method comprising:

capturing, by an imaging sensor on-board the satellite, a first image;

analyzing the first image to create analysis results, the analysis results including determining objects depicted within the first image;

determining, based upon analyzing the first image, a task to perform; and

performing the task.

17. The method as in claim 16, further comprising capturing a second image, wherein the second image is one or more of a higher resolution than the first image, a multispectral image, or a hyperspectral image.

18. The method as in claim 16, wherein the task to perform comprises changing an orientation of the satellite.

19. The method as in claim 16, wherein the task to perform comprises activating a payload of the satellite.

20. The method as in claim 16, wherein the satellite captures a plurality of images and the task to perform comprises sending less than the plurality of images to a ground station.

21. The method as in claim 16, wherein the task to perform comprises capturing a second image, the second image having a higher resolution than the first image, and detecting objects depicted in the second image.

22. The method as in claim 16, wherein the task to perform comprises transmitting the analysis results a location independent of the orbiting satellite.

23. The method as in claim 22, wherein the task to perform comprises counting a number of objects depicted in the first image and sending the number of objects to a ground station.

24. The method as in claim 16, wherein the task to perform is transmitted to a second satellite and the second satellite performs the task.

25. The method as in claim 16, wherein the task to perform is transmitted to a second satellite and the second satellite relays the task to a third satellite and the third satellite performs the task.