Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations
<p>Infrared thermal cameras offer reliable means of assessing atmospheric conditions by measuring the downward radiance from the sky, facilitating their usage in cloud monitoring endeavors. The precise identification and detection of clouds in images pose great challenges stemming from the ind...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-05-01
|
| Series: | Atmospheric Measurement Techniques |
| Online Access: | https://amt.copernicus.org/articles/18/2083/2025/amt-18-2083-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850274050830499840 |
|---|---|
| author | K. Sommer W. Kabalan R. Brunet |
| author_facet | K. Sommer W. Kabalan R. Brunet |
| author_sort | K. Sommer |
| collection | DOAJ |
| description | <p>Infrared thermal cameras offer reliable means of assessing atmospheric conditions by measuring the downward radiance from the sky, facilitating their usage in cloud monitoring endeavors. The precise identification and detection of clouds in images pose great challenges stemming from the indistinct boundaries inherent to cloud formations. Various methodologies for segmentation have been previously suggested. Most of them rely on color as the distinguishing criterion for cloud identification in the visible spectral domain and thus lack the ability to detect cloud structures in gray-scaled images with satisfying accuracy. In this work, we propose a new complete deep-learning framework to perform image classification and segmentation with convolutional neural networks. We demonstrate the effectiveness of this technique by conducting a series of tests and validations based on self-captured infrared sky images. Our findings reveal that the models can effectively differentiate between image types and accurately capture detailed cloud structure information at the pixel level, even when trained with a single binary ground-truth mask per input sample. The classifier model achieves an excellent accuracy of 99 % in image type distinction, while the segmentation model attains a mean pixel accuracy of 95 % in our dataset. We emphasize that our framework exhibits strong viability and can be used for infrared thermal ground-based cloud monitoring operations over extended durations. We expect to take advantage of this framework for astronomical applications by providing cloud cover selection criteria for ground-based photometric observations within the StarDICE experiment.</p> |
| format | Article |
| id | doaj-art-2337f92e0a4d4b1faf345147bf902e63 |
| institution | OA Journals |
| issn | 1867-1381 1867-8548 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Atmospheric Measurement Techniques |
| spelling | doaj-art-2337f92e0a4d4b1faf345147bf902e632025-08-20T01:51:15ZengCopernicus PublicationsAtmospheric Measurement Techniques1867-13811867-85482025-05-01182083210110.5194/amt-18-2083-2025Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observationsK. Sommer0W. Kabalan1R. Brunet2Laboratoire Univers et Particules de Montpellier, Université de Montpellier, CNRS, Montpellier, FranceAstroparticule et Cosmologie, Université Paris Cité, CNRS, 75013 Paris, FranceAix-Marseille Université, CNRS, CNES, LAM, Marseille, France<p>Infrared thermal cameras offer reliable means of assessing atmospheric conditions by measuring the downward radiance from the sky, facilitating their usage in cloud monitoring endeavors. The precise identification and detection of clouds in images pose great challenges stemming from the indistinct boundaries inherent to cloud formations. Various methodologies for segmentation have been previously suggested. Most of them rely on color as the distinguishing criterion for cloud identification in the visible spectral domain and thus lack the ability to detect cloud structures in gray-scaled images with satisfying accuracy. In this work, we propose a new complete deep-learning framework to perform image classification and segmentation with convolutional neural networks. We demonstrate the effectiveness of this technique by conducting a series of tests and validations based on self-captured infrared sky images. Our findings reveal that the models can effectively differentiate between image types and accurately capture detailed cloud structure information at the pixel level, even when trained with a single binary ground-truth mask per input sample. The classifier model achieves an excellent accuracy of 99 % in image type distinction, while the segmentation model attains a mean pixel accuracy of 95 % in our dataset. We emphasize that our framework exhibits strong viability and can be used for infrared thermal ground-based cloud monitoring operations over extended durations. We expect to take advantage of this framework for astronomical applications by providing cloud cover selection criteria for ground-based photometric observations within the StarDICE experiment.</p>https://amt.copernicus.org/articles/18/2083/2025/amt-18-2083-2025.pdf |
| spellingShingle | K. Sommer W. Kabalan R. Brunet Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations Atmospheric Measurement Techniques |
| title | Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations |
| title_full | Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations |
| title_fullStr | Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations |
| title_full_unstemmed | Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations |
| title_short | Infrared radiometric image classification and segmentation of cloud structures using a deep-learning framework from ground-based infrared thermal camera observations |
| title_sort | infrared radiometric image classification and segmentation of cloud structures using a deep learning framework from ground based infrared thermal camera observations |
| url | https://amt.copernicus.org/articles/18/2083/2025/amt-18-2083-2025.pdf |
| work_keys_str_mv | AT ksommer infraredradiometricimageclassificationandsegmentationofcloudstructuresusingadeeplearningframeworkfromgroundbasedinfraredthermalcameraobservations AT wkabalan infraredradiometricimageclassificationandsegmentationofcloudstructuresusingadeeplearningframeworkfromgroundbasedinfraredthermalcameraobservations AT rbrunet infraredradiometricimageclassificationandsegmentationofcloudstructuresusingadeeplearningframeworkfromgroundbasedinfraredthermalcameraobservations |