Development and Training of a Neural Network Filter for Satellite Images Processing
This paper is devoted to the study of the efficiency of using neural networks for filtering satellite images. The authors propose the use of convolutional noise suppressing autoencoders in order to minimize the filtering error variance. As part of the study, the architecture of the autoencoder was d...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2024-12-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-2-W5-2024/9/2024/isprs-archives-XLVIII-2-W5-2024-9-2024.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850249986333212672 |
|---|---|
| author | N. Andriyanov A. Kim |
| author_facet | N. Andriyanov A. Kim |
| author_sort | N. Andriyanov |
| collection | DOAJ |
| description | This paper is devoted to the study of the efficiency of using neural networks for filtering satellite images. The authors propose the use of convolutional noise suppressing autoencoders in order to minimize the filtering error variance. As part of the study, the architecture of the autoencoder was developed, optimal hyperparameters were selected and the resulting neural network model was trained. In addition, the paper compares the effectiveness of the proposed approach with traditional filtering algorithms such as Kalman filter and Wiener filter. Our models provide filtering efficiency gains of 3–4% at low noise levels (Signal-Noise-Ratio, SNR is 4 or more). The authors also investigated the effect of using data augmentations on improving the filtering quality. Experimental results showed that neural network models are able to outperform classical filters in terms of accuracy in processing real satellite images. Additionally, the paper studied the dependence of the filtering error variance on the number of training epochs of the neural network. The obtained results demonstrate that the developed neural network filter can be effectively applied for noise suppression on satellite images. |
| format | Article |
| id | doaj-art-391cc7536a144b58bead2a61436e2ae8 |
| institution | OA Journals |
| issn | 1682-1750 2194-9034 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj-art-391cc7536a144b58bead2a61436e2ae82025-08-20T01:58:20ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-12-01XLVIII-2-W5-202491410.5194/isprs-archives-XLVIII-2-W5-2024-9-2024Development and Training of a Neural Network Filter for Satellite Images ProcessingN. Andriyanov0A. Kim1Financial University under the Government of the Russian FederationFinancial University under the Government of the Russian FederationThis paper is devoted to the study of the efficiency of using neural networks for filtering satellite images. The authors propose the use of convolutional noise suppressing autoencoders in order to minimize the filtering error variance. As part of the study, the architecture of the autoencoder was developed, optimal hyperparameters were selected and the resulting neural network model was trained. In addition, the paper compares the effectiveness of the proposed approach with traditional filtering algorithms such as Kalman filter and Wiener filter. Our models provide filtering efficiency gains of 3–4% at low noise levels (Signal-Noise-Ratio, SNR is 4 or more). The authors also investigated the effect of using data augmentations on improving the filtering quality. Experimental results showed that neural network models are able to outperform classical filters in terms of accuracy in processing real satellite images. Additionally, the paper studied the dependence of the filtering error variance on the number of training epochs of the neural network. The obtained results demonstrate that the developed neural network filter can be effectively applied for noise suppression on satellite images.https://isprs-archives.copernicus.org/articles/XLVIII-2-W5-2024/9/2024/isprs-archives-XLVIII-2-W5-2024-9-2024.pdf |
| spellingShingle | N. Andriyanov A. Kim Development and Training of a Neural Network Filter for Satellite Images Processing The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | Development and Training of a Neural Network Filter for Satellite Images Processing |
| title_full | Development and Training of a Neural Network Filter for Satellite Images Processing |
| title_fullStr | Development and Training of a Neural Network Filter for Satellite Images Processing |
| title_full_unstemmed | Development and Training of a Neural Network Filter for Satellite Images Processing |
| title_short | Development and Training of a Neural Network Filter for Satellite Images Processing |
| title_sort | development and training of a neural network filter for satellite images processing |
| url | https://isprs-archives.copernicus.org/articles/XLVIII-2-W5-2024/9/2024/isprs-archives-XLVIII-2-W5-2024-9-2024.pdf |
| work_keys_str_mv | AT nandriyanov developmentandtrainingofaneuralnetworkfilterforsatelliteimagesprocessing AT akim developmentandtrainingofaneuralnetworkfilterforsatelliteimagesprocessing |