SILO: A Machine Learning Dataset of Synthetic Ground-Based Observations of LEO Satellites

Werth, M.; Lucas, Jacob; Kyono, Trent; McQuaid, Ian; Fletcher, Justin

doi:10.1109/aero47225.2020.9172251

Cited by 11 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the SDA enterprise, convolutional neural networks have been applied to object detection, detection of closely spaced objects, pose estimation, reconstruction of high resolution imagery, and segmentation of satellites. [2][3][4][5][6] In these examples, solutions learned from high contrast scientific imagery solve problems faster and more effectively than physics based methods.…”

Section: Learned Space Domain Awarenessmentioning

confidence: 99%

The potential for satellite recognition from ground-based filter photometry

Gazak,

Phelps,

Swindle

et al. 2023

Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXIX

View full text Add to dashboard Cite

Recent work demonstrates recognition of artificial satellites in spatially unresolved observations by utilizing learned spectroscopic classification (SpectraNet 1 ). That proof of concept exposes critical identifying information currently lacking in catalogs used by space domain awareness stakeholders. In this work we present experiments to increase the accessibility and efficiency of SpectraNet enabled systems by probing the bandpass and resolution requirements for learned recognition of satellites. To enable affordable, off the shelf instrumentation, this work focuses on wavelength ranges accessible by Silicon-based detectors (400-1000 nanometers). While the SpectraNet proof of concept utilized a medium resolution spectrograph on a 3.6 meter telescope at 10,000 feet elevation, we show that the identifying spectral features relate to an object's overall spectral energy density and are accessible at significantly lower spectral resolution. This finding relaxes the need for large telescopes at high altitude. We further demonstrate that the technology can be utilized via simultaneous multi-band filter photometry. Design considerations for properly obtaining simultaneous photometry are discussed. Thus this work demonstrates that−in simulation−learned spectral recognition is an effective technology from high resolution spectrographs through simultaneous multi-filter photometric instruments. We provide experiments to understand the minimum engineered system needed to perform effective learned recognition, such that the technology can be hardened and widely proliferated.

show abstract

Section: Learned Space Domain Awarenessmentioning

confidence: 99%

The potential for satellite recognition from ground-based filter photometry

Gazak,

Phelps,

Swindle

et al. 2023

Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXIX

View full text Add to dashboard Cite

show abstract

“…C 2 n (z) is a measure of turbulence strength. Equation (3) suggests that the distance z should satisfy the criteria of the Fraunhofer far-field condition [20] in order to simplify the spherical wave emitted by a point source to a planar wave. It can be quantified by…”

Section: Modeling Phase Screens By Atmospheric Turbulencementioning

confidence: 99%

“…However, the ability to observe and track LEO targets using on-Earth telescopes holds great importance for various applications, such as space surveillance and orbital debris monitoring. Overcoming these challenges and improving image quality are crucial for enhancing our understanding of LEO objects and their behaviors [2,3]. Large apertures enable the collection of more light from faint celestial bodies and allow for more accurate observations with higher resolution.…”

Section: Introductionmentioning

confidence: 99%

On-Earth Observation of Low Earth Orbit Targets through Phase Disturbances by Atmospheric Turbulence

Wang,

Yu,

Gong

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

This paper addresses the challenges of ground-based observation of Low Earth Orbit (LEO) targets using on-Earth telescopes and proposes solutions for improving image quality and tracking fast-moving objects under atmospheric turbulence conditions. The study investigates major challenges, including atmospheric turbulence-induced aberrations, blurring, telescope platform vibrations, and spatial variations caused by the target motion. A scenario simulation is conducted considering practical limitations, such as feasible time slots for monitoring and the number of available frames within the Field of View (FoV). The paper proposes a novel method for detecting LEO targets using Harris corner features and matching adjacent images upon the corrected frames by Adaptive Optics (AO), with a 38% reduction in the Mean Squared Error (MSE) achieved for certain frames within the isoplanatic angle. Additionally, a refinement strategy for deblurring images is proposed, combining the post-processing with Singular Value Decomposition (SVD) filtering; with a proper filtering factor (β=0.1), an almost complete collection of 14 corner nodes can be detected. The feasibility of continuously tracking objects with uncontrolled attitudes, such as space debris, is successfully demonstrated with continuous monitoring of certain features. The proposed methods offer promising solutions for ground-based observation of LEO targets, providing insights for further research and application in this field.

show abstract

“…14 Opportunistic navigation using deep learning (DL), machine learning, and neural networks was also investigated for LEO/INS-aided and multi-path environments. [15][16][17] Moreover, a navigation algorithm using two Orbcomm satellites was designed for an unmanned aerial vehicle (UAV) in 18 , while new positioning algorithms were designed for the weak signals and normal environments using multiple Iridium satellites in 19,20 . Both algorithms showed mere positioning accuracy improvement compared to the stand-alone INS solution.…”

Section: Literature Reviewmentioning

confidence: 99%

High-order pseudorange rate measurement model for multi-constellation LEO/INS integration: Case of Iridium-NEXT, Orbcomm, and Globalstar

Farhangian

Landry

2022

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

An inertial navigation method augmented by Signals of Opportunity (SOPs) of three low earth orbit (LEO) constellations is presented. The downlink signal characteristics of the Iridium-NEXT, Orbcomm, and Globalstar LEO constellations are discussed. Furthermore, a tightly coupled integration model of the inertial navigation system and high-order LEO-SOP Doppler measurement model is designed. We presented a second-order measurement model of the LEO-SOP/INS integration using a second-order extended Kalman filter in which all the unknown states of the receiver and LEO satellites are estimated. The state parameters of the second-order EKF model are the position and velocity of both the receiver and the satellites, as well as the receiver’s orientation, the clock bias, and clock drift of the LEO satellites, and the constant bias of the Inertial Measurement Unit. An experiment is performed using a ground aerial vehicle equipped with a Multi-Constellation Software-Defined Receiver (MC-SDR). The Doppler measurements are provided by observing the downlinks from multiple satellites of the Iridium-NEXT and Orbcomm constellations. As well, the predicted measurement of a Globalstar satellite is used in the designed model. The results show the positioning accuracy of less than 10 m being achieved during a dynamic ground experiment, representing an 82% precision gain as compared against the regular single constellation EKF method.

show abstract

SILO: A Machine Learning Dataset of Synthetic Ground-Based Observations of LEO Satellites

Cited by 11 publications

References 30 publications

The potential for satellite recognition from ground-based filter photometry

The potential for satellite recognition from ground-based filter photometry

On-Earth Observation of Low Earth Orbit Targets through Phase Disturbances by Atmospheric Turbulence

High-order pseudorange rate measurement model for multi-constellation LEO/INS integration: Case of Iridium-NEXT, Orbcomm, and Globalstar

Contact Info

Product

Resources

About