Onboard AI-based Cloud Detection System for Enhanced Satellite Autonomy Using PUS

Patent metadata

Field	Value
Publication number	US-2022366684-A1
Application number	US-202217709505-A
Country	US
Kind code	A1
Filing date	Mar 31, 2022
Priority date	May 11, 2021
Publication date	Nov 17, 2022
Grant date	—

Abstract

An onboard cloud detection system comprising: a camera (1000) configured to acquire images of the Earth at predetermined acquisition intervals; and a data processing unit (2000) comprising: a cloud detection unit (2210) configured to use artificial intelligence, AI, algorithms to detect clouds; a packet utilization standard, PUS, application layer (2230) configured to issue telemetry and/or telecommands corresponding to a predetermined parameter of the output of the cloud detection unit (2210); and an interface configured to distribute the telemetry and/or telecommands to an external hardware and/or an external software terminal (3000, 4000).

First claim

1 . An onboard cloud detection system comprising:
a camera configured to acquire images of the Earth at predetermined acquisition intervals; and a data processing unit comprising: a cloud detection unit configured to use artificial intelligence, AI, algorithms to detect clouds; a packet utilization standard, PUS, application layer configured to issue telemetry and/or telecommands corresponding to a predetermined parameter of the output of the cloud detection unit; and an interface configured to distribute the telemetry and/or telecommands to an external hardware and/or an external software terminal.

2 . The onboard cloud detection system of claim 1 , wherein the telemetry and/or telecommands are configured to enable and/or disable the main payload directly or via the on-board computer, wherein the enabling and/or disabling of the main payload is configured to be triggered according to the predetermined parameter.

3 . The onboard cloud detection system of claim 1 , wherein the AI algorithms are configured to be based upon deep learning and/or machine learning.

4 . The onboard cloud detection system of claim 1 , further comprising a threshold detection unit configured to detect if the predetermined parameter is above or below a predefined threshold.

5 . The onboard cloud detection system of claim 1 , wherein the predetermined parameter is a percentage of one of the acquired images covered by clouds.

6 . The onboard cloud detection system of claim 2 , wherein the predetermined parameter is a percentage of one of the acquired images covered by clouds, and wherein the main payload is configured to be enabled and/or disabled if the percentage of the image covered by clouds is above or below the predetermined threshold.

7 . The onboard cloud detection system of claim 4 , wherein the SW application layer is configured to count a number of consecutive inputs where the predetermined parameter is above or below the predefined threshold.

8 . The onboard cloud detection system of claim 1 , wherein the predetermined acquisition intervals are controlled by a time scheduling service and/or an orbit position scheduling service.

9 . A satellite comprising the onboard cloud detection system of claim 1 .

10 . A method for operating an onboard cloud detection system comprising:
acquiring images of the Earth at predetermined acquisition intervals by a camera; detecting clouds, by artificial intelligence, AI, algorithms, in a cloud detection unit; issuing telemetry and/or telecommands corresponding to a predetermined parameter of the output of the cloud detection unit by a packet utilization standard, PUS, application layer; and distributing the telemetry and/or telecommands to an external hardware and/or an external software terminal by an interface.

11 . The method of claim 10 , further comprising enabling and/or disabling the main payload directly or via the on-board computer, wherein the enabling and/or disabling of the main payload is configured to be triggered according to the predetermined parameter.

12 . The method of claim 10 , further comprising detecting if the predetermined parameter is above or below a predefined threshold by a threshold detection unit.

13 . The method of claim 10 , wherein the predetermined parameter is a percentage of one of the acquired images covered by clouds.

14 . The method of claim 11 , wherein the predetermined parameter is a percentage of one of the acquired images covered by clouds, and wherein the enabling and/or disabling of the main payload occurs if the number of consecutive images covered by clouds is above or below the predetermined threshold.

15 . The method of claim 10 , wherein the predetermined acquisition intervals are controlled by a time scheduling service and/or a position scheduling service.

Assignees

• Airbus Defence & Space Gmbh

Inventors

• Ales Filippo
• Fritz Michael
• Krstova Alisa

Classifications

• G06F18/24133

  Distances to prototypes · CPC title

• G06V20/13 Primary

  Satellite images · CPC title

• G06V10/70

  using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88) · CPC title

• H04L67/12

  specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title