Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation Patterns
This study introduces electro-optical (EO) sensors (TurbNet sensors) that utilize a remote laser beacon (either coherent or incoherent) and an optical receiver with CCD camera and embedded edge AI computer (Jetson Xavier Nx) for in situ evaluation of the path-averaged atmospheric turbulence refracti...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Photonics |
Subjects: | |
Online Access: | https://www.mdpi.com/2304-6732/9/11/789 |
_version_ | 1797466820645486592 |
---|---|
author | Ernst Polnau Don L. N. Hettiarachchi Mikhail A. Vorontsov |
author_facet | Ernst Polnau Don L. N. Hettiarachchi Mikhail A. Vorontsov |
author_sort | Ernst Polnau |
collection | DOAJ |
description | This study introduces electro-optical (EO) sensors (TurbNet sensors) that utilize a remote laser beacon (either coherent or incoherent) and an optical receiver with CCD camera and embedded edge AI computer (Jetson Xavier Nx) for in situ evaluation of the path-averaged atmospheric turbulence refractive index structure parameter <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>C</mi><mi>n</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> at a high temporal rate. Evaluation of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>C</mi><mi>n</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> values was performed using deep neural network (DNN)-based real-time processing of short-exposure laser-beacon light intensity scintillation patterns (images) captured by a TurbNet sensor optical receiver. Several pre-trained DNN models were loaded onto the AI computer and used for TurbNet sensor performance evaluation in a set of atmospheric propagation inference trials under diverse turbulence and meteorological conditions. DNN model training, validation, and testing were performed using datasets comprised of a large number of instances of scintillation frames and corresponding reference (“true”) <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>C</mi><mi>n</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> values that were measured side-by-side with a commercial scintillometer (BLS 2000). Generation of datasets and inference trials was performed at the University of Dayton’s (UD) 7-km atmospheric propagation test range. The results demonstrated a 70–90% correlation between <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>C</mi><mi>n</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> values obtained with the TurbNet sensors and those measured side-by-side with the scintillometer. |
first_indexed | 2024-03-09T18:45:05Z |
format | Article |
id | doaj.art-76be579f3a3d4f8783c97c5b7ebe6000 |
institution | Directory Open Access Journal |
issn | 2304-6732 |
language | English |
last_indexed | 2024-03-09T18:45:05Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Photonics |
spelling | doaj.art-76be579f3a3d4f8783c97c5b7ebe60002023-11-24T06:22:20ZengMDPI AGPhotonics2304-67322022-10-0191178910.3390/photonics9110789Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation PatternsErnst Polnau0Don L. N. Hettiarachchi1Mikhail A. Vorontsov2Intelligent Optics Laboratory, School of Engineering, University of Dayton, 300 College Park, Dayton, OH 45469, USAIntelligent Optics Laboratory, School of Engineering, University of Dayton, 300 College Park, Dayton, OH 45469, USAIntelligent Optics Laboratory, School of Engineering, University of Dayton, 300 College Park, Dayton, OH 45469, USAThis study introduces electro-optical (EO) sensors (TurbNet sensors) that utilize a remote laser beacon (either coherent or incoherent) and an optical receiver with CCD camera and embedded edge AI computer (Jetson Xavier Nx) for in situ evaluation of the path-averaged atmospheric turbulence refractive index structure parameter <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>C</mi><mi>n</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> at a high temporal rate. Evaluation of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>C</mi><mi>n</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> values was performed using deep neural network (DNN)-based real-time processing of short-exposure laser-beacon light intensity scintillation patterns (images) captured by a TurbNet sensor optical receiver. Several pre-trained DNN models were loaded onto the AI computer and used for TurbNet sensor performance evaluation in a set of atmospheric propagation inference trials under diverse turbulence and meteorological conditions. DNN model training, validation, and testing were performed using datasets comprised of a large number of instances of scintillation frames and corresponding reference (“true”) <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>C</mi><mi>n</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> values that were measured side-by-side with a commercial scintillometer (BLS 2000). Generation of datasets and inference trials was performed at the University of Dayton’s (UD) 7-km atmospheric propagation test range. The results demonstrated a 70–90% correlation between <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>C</mi><mi>n</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> values obtained with the TurbNet sensors and those measured side-by-side with the scintillometer.https://www.mdpi.com/2304-6732/9/11/789atmospheric turbulencedeep neural networkelectro-optics sensorembedded edge AI computingNVIDIA Jetson Xavier Nxreal-time sensing |
spellingShingle | Ernst Polnau Don L. N. Hettiarachchi Mikhail A. Vorontsov Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation Patterns Photonics atmospheric turbulence deep neural network electro-optics sensor embedded edge AI computing NVIDIA Jetson Xavier Nx real-time sensing |
title | Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation Patterns |
title_full | Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation Patterns |
title_fullStr | Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation Patterns |
title_full_unstemmed | Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation Patterns |
title_short | Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation Patterns |
title_sort | electro optical sensors for atmospheric turbulence strength characterization with embedded edge ai processing of scintillation patterns |
topic | atmospheric turbulence deep neural network electro-optics sensor embedded edge AI computing NVIDIA Jetson Xavier Nx real-time sensing |
url | https://www.mdpi.com/2304-6732/9/11/789 |
work_keys_str_mv | AT ernstpolnau electroopticalsensorsforatmosphericturbulencestrengthcharacterizationwithembeddededgeaiprocessingofscintillationpatterns AT donlnhettiarachchi electroopticalsensorsforatmosphericturbulencestrengthcharacterizationwithembeddededgeaiprocessingofscintillationpatterns AT mikhailavorontsov electroopticalsensorsforatmosphericturbulencestrengthcharacterizationwithembeddededgeaiprocessingofscintillationpatterns |