Simulation of RSO Images for Space Situation Awareness (SSA) Using Parallel Processing
With the rapid increase in resident space objects (RSO), there is a growing demand for their identification and characterization to advance space simulation awareness (SSA) programs. Various AI-based technologies are proposed and demonstrated around the world to effectively and efficiently identify...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/23/7868 |
_version_ | 1797507215788081152 |
---|---|
author | Ryan Clark Yanchun Fu Siddharth Dave Regina Lee |
author_facet | Ryan Clark Yanchun Fu Siddharth Dave Regina Lee |
author_sort | Ryan Clark |
collection | DOAJ |
description | With the rapid increase in resident space objects (RSO), there is a growing demand for their identification and characterization to advance space simulation awareness (SSA) programs. Various AI-based technologies are proposed and demonstrated around the world to effectively and efficiently identify RSOs from ground and space-based observations; however, there remains a challenge in AI training due to the lack of labeled datasets for accurate RSO detection. In this paper, we present an overview of the starfield simulator to generate a realistic representation of images from space-borne imagers. In particular, we focus on low-resolution images such as those taken with a commercial-grade star tracker that contains various RSO in starfield images. The accuracy and computational efficiency of the simulator are compared to the commercial simulator, namely STK-EOIR to demonstrate the performance of the simulator. In comparing over 1000 images from the Fast Auroral Imager (FAI) onboard CASSIOPE satellite, the current simulator generates both stars and RSOs with approximately the same accuracy (compared to the real images) as STK-EOIR and, an order of magnitude faster in computational speed by leveraging parallel processing methodologies. |
first_indexed | 2024-03-10T04:45:23Z |
format | Article |
id | doaj.art-5da07f7eca534e0aa5812225beb72dc1 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T04:45:23Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-5da07f7eca534e0aa5812225beb72dc12023-11-23T03:00:22ZengMDPI AGSensors1424-82202021-11-012123786810.3390/s21237868Simulation of RSO Images for Space Situation Awareness (SSA) Using Parallel ProcessingRyan Clark0Yanchun Fu1Siddharth Dave2Regina Lee3Department of Earth and Space Science, York University, 4700 Keele Street, Toronto, ON M3J 1P3, CanadaDepartment of Earth and Space Science, York University, 4700 Keele Street, Toronto, ON M3J 1P3, CanadaDepartment of Earth and Space Science, York University, 4700 Keele Street, Toronto, ON M3J 1P3, CanadaDepartment of Earth and Space Science, York University, 4700 Keele Street, Toronto, ON M3J 1P3, CanadaWith the rapid increase in resident space objects (RSO), there is a growing demand for their identification and characterization to advance space simulation awareness (SSA) programs. Various AI-based technologies are proposed and demonstrated around the world to effectively and efficiently identify RSOs from ground and space-based observations; however, there remains a challenge in AI training due to the lack of labeled datasets for accurate RSO detection. In this paper, we present an overview of the starfield simulator to generate a realistic representation of images from space-borne imagers. In particular, we focus on low-resolution images such as those taken with a commercial-grade star tracker that contains various RSO in starfield images. The accuracy and computational efficiency of the simulator are compared to the commercial simulator, namely STK-EOIR to demonstrate the performance of the simulator. In comparing over 1000 images from the Fast Auroral Imager (FAI) onboard CASSIOPE satellite, the current simulator generates both stars and RSOs with approximately the same accuracy (compared to the real images) as STK-EOIR and, an order of magnitude faster in computational speed by leveraging parallel processing methodologies.https://www.mdpi.com/1424-8220/21/23/7868space situational awareness (SSA)resident space objects (RSOs)artificial intelligence (AI)parallel processing |
spellingShingle | Ryan Clark Yanchun Fu Siddharth Dave Regina Lee Simulation of RSO Images for Space Situation Awareness (SSA) Using Parallel Processing Sensors space situational awareness (SSA) resident space objects (RSOs) artificial intelligence (AI) parallel processing |
title | Simulation of RSO Images for Space Situation Awareness (SSA) Using Parallel Processing |
title_full | Simulation of RSO Images for Space Situation Awareness (SSA) Using Parallel Processing |
title_fullStr | Simulation of RSO Images for Space Situation Awareness (SSA) Using Parallel Processing |
title_full_unstemmed | Simulation of RSO Images for Space Situation Awareness (SSA) Using Parallel Processing |
title_short | Simulation of RSO Images for Space Situation Awareness (SSA) Using Parallel Processing |
title_sort | simulation of rso images for space situation awareness ssa using parallel processing |
topic | space situational awareness (SSA) resident space objects (RSOs) artificial intelligence (AI) parallel processing |
url | https://www.mdpi.com/1424-8220/21/23/7868 |
work_keys_str_mv | AT ryanclark simulationofrsoimagesforspacesituationawarenessssausingparallelprocessing AT yanchunfu simulationofrsoimagesforspacesituationawarenessssausingparallelprocessing AT siddharthdave simulationofrsoimagesforspacesituationawarenessssausingparallelprocessing AT reginalee simulationofrsoimagesforspacesituationawarenessssausingparallelprocessing |