SAR Image Despeckling Based on GO Distribution
Xiangli Nie; Bo Zhang; Hong Qiao; Suiwu Zheng
2013
Conference NameInternational Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC)
Source PublicationInternational Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC)
Conference DateDec 20-22, 2013
Conference PlaceShenyang, China
AbstractAbstract-In this paper, we propose a new model for synthetic aperture radar (SAR) image despeckling based on the GO statistical distribution and nonlocal total variation regularization. By taking the distribution of the backscatter into account, a new data fidelity term is derived by the maximum a posteriori Bayesian rule. Combining the new fidelity term with the nonlocal total variation regularization gives a new variational model for SAR image despeckling. The primal-dual algorithm framework is then used to solve the new variational problem. Experimental results on real SAR images demonstrate the validity of the proposed method.
KeywordSynthetic Aperture Radar (Sar) G-zero Distribution Maximum a Posteriori (Map) Speckle Nonlocal Total Variation (Nl-tv) Primal-dual Algorithm
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13004
Collection复杂系统管理与控制国家重点实验室_机器人理论与应用
Corresponding AuthorXiangli Nie
Recommended Citation
GB/T 7714
Xiangli Nie,Bo Zhang,Hong Qiao,et al. SAR Image Despeckling Based on GO Distribution[C],2013.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiangli Nie]'s Articles
[Bo Zhang]'s Articles
[Hong Qiao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiangli Nie]'s Articles
[Bo Zhang]'s Articles
[Hong Qiao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiangli Nie]'s Articles
[Bo Zhang]'s Articles
[Hong Qiao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.