Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image
Overexposure may happen for imaging of solar observation as extremely violet solar bursts occur, which means that signal intensity goes beyond the dynamic range of imaging system of a telescope, resulting in loss of signal. For example, during solar flare, Atmospheric Imaging Assembly (AIA) of Solar...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Advances in Astronomy |
| Online Access: | http://dx.doi.org/10.1155/2019/5343254 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832549131193679872 |
|---|---|
| author | Dong Zhao Long Xu Linjie Chen Yihua Yan Ling-Yu Duan |
| author_facet | Dong Zhao Long Xu Linjie Chen Yihua Yan Ling-Yu Duan |
| author_sort | Dong Zhao |
| collection | DOAJ |
| description | Overexposure may happen for imaging of solar observation as extremely violet solar bursts occur, which means that signal intensity goes beyond the dynamic range of imaging system of a telescope, resulting in loss of signal. For example, during solar flare, Atmospheric Imaging Assembly (AIA) of Solar Dynamics Observatory (SDO) often records overexposed images/videos, resulting loss of fine structures of solar flare. This paper makes effort to retrieve/recover missing information of overexposure by exploiting deep learning for its powerful nonlinear representation which makes it widely used in image reconstruction/restoration. First, a new model, namely, mask-Pix2Pix network, is proposed for overexposure recovery. It is built on a well-known Pix2Pix network of conditional generative adversarial network (cGAN). In addition, a hybrid loss function, including an adversarial loss, a masked L1 loss and a edge mass loss/smoothness, are integrated together for addressing challenges of overexposure relative to conventional image restoration. Moreover, a new database of overexposure is established for training the proposed model. Extensive experimental results demonstrate that the proposed mask-Pix2Pix network can well recover missing information of overexposure and outperforms the state of the arts originally designed for image reconstruction tasks. |
| format | Article |
| id | doaj-art-e8988a8b38a6435486c9a7fce9ea5635 |
| institution | Kabale University |
| issn | 1687-7969 1687-7977 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Astronomy |
| spelling | doaj-art-e8988a8b38a6435486c9a7fce9ea56352025-02-03T06:12:11ZengWileyAdvances in Astronomy1687-79691687-79772019-01-01201910.1155/2019/53432545343254Mask-Pix2Pix Network for Overexposure Region Recovery of Solar ImageDong Zhao0Long Xu1Linjie Chen2Yihua Yan3Ling-Yu Duan4Key Laboratory of Solar Activity, National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, ChinaKey Laboratory of Solar Activity, National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, ChinaKey Laboratory of Solar Activity, National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, ChinaKey Laboratory of Solar Activity, National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, ChinaNational Engineering Lab for Video Technology, Peking University, Beijing 100871, ChinaOverexposure may happen for imaging of solar observation as extremely violet solar bursts occur, which means that signal intensity goes beyond the dynamic range of imaging system of a telescope, resulting in loss of signal. For example, during solar flare, Atmospheric Imaging Assembly (AIA) of Solar Dynamics Observatory (SDO) often records overexposed images/videos, resulting loss of fine structures of solar flare. This paper makes effort to retrieve/recover missing information of overexposure by exploiting deep learning for its powerful nonlinear representation which makes it widely used in image reconstruction/restoration. First, a new model, namely, mask-Pix2Pix network, is proposed for overexposure recovery. It is built on a well-known Pix2Pix network of conditional generative adversarial network (cGAN). In addition, a hybrid loss function, including an adversarial loss, a masked L1 loss and a edge mass loss/smoothness, are integrated together for addressing challenges of overexposure relative to conventional image restoration. Moreover, a new database of overexposure is established for training the proposed model. Extensive experimental results demonstrate that the proposed mask-Pix2Pix network can well recover missing information of overexposure and outperforms the state of the arts originally designed for image reconstruction tasks.http://dx.doi.org/10.1155/2019/5343254 |
| spellingShingle | Dong Zhao Long Xu Linjie Chen Yihua Yan Ling-Yu Duan Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image Advances in Astronomy |
| title | Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image |
| title_full | Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image |
| title_fullStr | Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image |
| title_full_unstemmed | Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image |
| title_short | Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image |
| title_sort | mask pix2pix network for overexposure region recovery of solar image |
| url | http://dx.doi.org/10.1155/2019/5343254 |
| work_keys_str_mv | AT dongzhao maskpix2pixnetworkforoverexposureregionrecoveryofsolarimage AT longxu maskpix2pixnetworkforoverexposureregionrecoveryofsolarimage AT linjiechen maskpix2pixnetworkforoverexposureregionrecoveryofsolarimage AT yihuayan maskpix2pixnetworkforoverexposureregionrecoveryofsolarimage AT lingyuduan maskpix2pixnetworkforoverexposureregionrecoveryofsolarimage |