Exploration of U-Net in Automated Solar Coronal Loop Segmentation
| Autor: | Shadi Moradi, Qing Tian, Jong Kwan Lee |
|---|---|
| Přispěvatelé: | Skala, Václav |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Physics
business.industry segmentation ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION convolutional neural network Coronal loop konvoluční neuronová síť Real image Corona Convolutional neural network U-Net segmentace aplikace solární fyziky Solar Physics Application Observatory Computer Science::Computer Vision and Pattern Recognition Physics::Space Physics Astrophysics::Solar and Stellar Astrophysics Segmentation Computer vision Artificial intelligence business |
| Popis: | This paper presents a deep convolutional neural network (CNN) based method that automatically segments arc- like structures of coronal loops from the intensity images of Sun’s corona. The method explores multiple U-Net architecture variants which enable segmentation of coronal loop structures of active regions from NASA’s Solar Dynamic Observatory (SDO) imagery. The effectiveness of the method is evaluated through experiments on both synthetic and real images, and the results show that the method segments the coronal loop structures accurately. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|