Atmospheric Turbulence Intensity Image Acquisition Method Based on Convolutional Neural Network
An algorithmic model of a neural network with channel attention and spatial attention (CASANet) is proposed to estimate the value of atmospheric coherence length, which in turn provides a quantitative description of atmospheric turbulence intensity. By processing the acquired spot image data, the ch...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/103 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548972724846592 |
|---|---|
| author | Yuan Mu Liangping Zhou Shiyong Shao Zhiqiang Wang Pei Tang Zhiyuan Hu Liwen Ye |
| author_facet | Yuan Mu Liangping Zhou Shiyong Shao Zhiqiang Wang Pei Tang Zhiyuan Hu Liwen Ye |
| author_sort | Yuan Mu |
| collection | DOAJ |
| description | An algorithmic model of a neural network with channel attention and spatial attention (CASANet) is proposed to estimate the value of atmospheric coherence length, which in turn provides a quantitative description of atmospheric turbulence intensity. By processing the acquired spot image data, the channel attention and spatial attention mechanisms are utilized, and the convolutional neural network learns the interdependence between the channel and space of the feature image and adaptively recalibrates the feature response in terms of the channel to increase the contribution of the foreground spot and suppress the background features. Based on the experimental data, an analysis of the CASANet model subject to turbulence intensity perturbations, fluctuations in outgoing power, and fluctuations in beam quality at the outlet is carried out. Comparison of the results of the convolutional neural network with those of the inverse method and the differential image motion method shows that the convolutional neural network is optimal in three evaluation indexes, namely, the mean deviation, the root-mean-square error, and the correlation coefficient, which are 2.74, 3.35, and 0.94, respectively. The convolutional neural network exhibits high accuracy under moderate and weak turbulence, and the estimation values under strong turbulence conditions are still mostly within the 95% confidence interval. The above results fully demonstrate that the proposed convolutional neural network method can effectively estimate the atmospheric coherence length, which provides technical support for the inversion of atmospheric turbulence intensity based on images. |
| format | Article |
| id | doaj-art-1d2439f7359d4093ad1f0d9af29e7328 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-1d2439f7359d4093ad1f0d9af29e73282025-01-10T13:20:13ZengMDPI AGRemote Sensing2072-42922024-12-0117110310.3390/rs17010103Atmospheric Turbulence Intensity Image Acquisition Method Based on Convolutional Neural NetworkYuan Mu0Liangping Zhou1Shiyong Shao2Zhiqiang Wang3Pei Tang4Zhiyuan Hu5Liwen Ye6Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaKey Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaAn algorithmic model of a neural network with channel attention and spatial attention (CASANet) is proposed to estimate the value of atmospheric coherence length, which in turn provides a quantitative description of atmospheric turbulence intensity. By processing the acquired spot image data, the channel attention and spatial attention mechanisms are utilized, and the convolutional neural network learns the interdependence between the channel and space of the feature image and adaptively recalibrates the feature response in terms of the channel to increase the contribution of the foreground spot and suppress the background features. Based on the experimental data, an analysis of the CASANet model subject to turbulence intensity perturbations, fluctuations in outgoing power, and fluctuations in beam quality at the outlet is carried out. Comparison of the results of the convolutional neural network with those of the inverse method and the differential image motion method shows that the convolutional neural network is optimal in three evaluation indexes, namely, the mean deviation, the root-mean-square error, and the correlation coefficient, which are 2.74, 3.35, and 0.94, respectively. The convolutional neural network exhibits high accuracy under moderate and weak turbulence, and the estimation values under strong turbulence conditions are still mostly within the 95% confidence interval. The above results fully demonstrate that the proposed convolutional neural network method can effectively estimate the atmospheric coherence length, which provides technical support for the inversion of atmospheric turbulence intensity based on images.https://www.mdpi.com/2072-4292/17/1/103atmospheric turbulenceneural networkimage processing |
| spellingShingle | Yuan Mu Liangping Zhou Shiyong Shao Zhiqiang Wang Pei Tang Zhiyuan Hu Liwen Ye Atmospheric Turbulence Intensity Image Acquisition Method Based on Convolutional Neural Network Remote Sensing atmospheric turbulence neural network image processing |
| title | Atmospheric Turbulence Intensity Image Acquisition Method Based on Convolutional Neural Network |
| title_full | Atmospheric Turbulence Intensity Image Acquisition Method Based on Convolutional Neural Network |
| title_fullStr | Atmospheric Turbulence Intensity Image Acquisition Method Based on Convolutional Neural Network |
| title_full_unstemmed | Atmospheric Turbulence Intensity Image Acquisition Method Based on Convolutional Neural Network |
| title_short | Atmospheric Turbulence Intensity Image Acquisition Method Based on Convolutional Neural Network |
| title_sort | atmospheric turbulence intensity image acquisition method based on convolutional neural network |
| topic | atmospheric turbulence neural network image processing |
| url | https://www.mdpi.com/2072-4292/17/1/103 |
| work_keys_str_mv | AT yuanmu atmosphericturbulenceintensityimageacquisitionmethodbasedonconvolutionalneuralnetwork AT liangpingzhou atmosphericturbulenceintensityimageacquisitionmethodbasedonconvolutionalneuralnetwork AT shiyongshao atmosphericturbulenceintensityimageacquisitionmethodbasedonconvolutionalneuralnetwork AT zhiqiangwang atmosphericturbulenceintensityimageacquisitionmethodbasedonconvolutionalneuralnetwork AT peitang atmosphericturbulenceintensityimageacquisitionmethodbasedonconvolutionalneuralnetwork AT zhiyuanhu atmosphericturbulenceintensityimageacquisitionmethodbasedonconvolutionalneuralnetwork AT liwenye atmosphericturbulenceintensityimageacquisitionmethodbasedonconvolutionalneuralnetwork |