Solar Filament Segmentation Based on Improved U-Nets
Document Type
Article
Publication Date
12-1-2021
Abstract
To detect, track and characterize solar filaments more accurately, novel filament segmentation methods based on improved U-Nets are proposed. The full-disk Hα images from the Huairou Solar Observing Station of the National Astronomical Observatory and the Big Bear Solar Observatory were used for training and verifying the effectiveness of different improved networks’ filament segmentation performance. Comparative experiments with different solar dataset sizes and input image quality were performed. The impact of each improvement method on the segmentation effect was analyzed and compared based on experimental results. In order to further explore the influence of network depth on filament-segmentation accuracy, the segmentation results produced by Conditional Generative Adversarial Networks (CGAN) were obtained and compared with improved U-nets. Experiments verified that U-Net with an Atrous Spatial Pyramid Pooling Module performs better for high-quality input solar images regardless of dataset sizes. CGAN performs better for low-quality input solar images with large dataset size. The algorithm may provide guidance for filament segmentation and more accurate segmentation results with less noise were acquired.
Identifier
85121553423 (Scopus)
Publication Title
Solar Physics
External Full Text Location
https://doi.org/10.1007/s11207-021-01920-3
e-ISSN
1573093X
ISSN
00380938
Issue
12
Volume
296
Grant
KLSA202114
Fund Ref
Chinese Academy of Sciences
Recommended Citation
Liu, Dan; Song, Wei; Lin, Ganghua; and Wang, Haimin, "Solar Filament Segmentation Based on Improved U-Nets" (2021). Faculty Publications. 3639.
https://digitalcommons.njit.edu/fac_pubs/3639