Remote sensing image restoration based on zero-norm regularized kernel estimation

YAN Jing-wen; PENG Hong; LIU Lei; JIN Guang; ZHONG Xing

doi:10.3788/OPE.20142209.2572

您当前的位置：

首页 >

文章列表页 >

Remote sensing image restoration based on zero-norm regularized kernel estimation

更新时间：2020-08-13

- Remote sensing image restoration based on zero-norm regularized kernel estimation
- Optics and Precision Engineering Vol. 22, Issue 9, Pages: 2572-2579(2014)
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 汕头大学工学院,广东汕头,515063
  3. 汕头大学数学系,广东汕头,515063
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20142209.2572
  CLC： TP751.1
- Received：11 June 2014，
  
  Revised：19 June 2014，
  
  Published：2014
- 稿件说明：
移动端阅览
闫敬文, 彭鸿, 刘蕾等. 基于L0正则化模糊核估计的遥感图像复原[J]. 光学精密工程, 2014,22(9): 2572-2579

YAN Jing-wen, PENG Hong, LIU Lei etc. Remote sensing image restoration based on zero-norm regularized kernel estimation[J]. Editorial Office of Optics and Precision Engineering, 2014,22(9): 2572-2579
闫敬文, 彭鸿, 刘蕾等. 基于L0正则化模糊核估计的遥感图像复原[J]. 光学精密工程, 2014,22(9): 2572-2579 DOI： 10.3788/OPE.20142209.2572.

YAN Jing-wen, PENG Hong, LIU Lei etc. Remote sensing image restoration based on zero-norm regularized kernel estimation[J]. Editorial Office of Optics and Precision Engineering, 2014,22(9): 2572-2579 DOI： 10.3788/OPE.20142209.2572.

摘要

基于模糊图像的退化过程、卷积模糊模型和模糊图像生成的机理，提出一种基于

范数的正则化模糊核估计方法，解决了遥感图像重建问题中0范数难求解的难题。该方法以模糊核稀疏性为先验知识，采用对应梯度的

范数为正则项，有效避免了细小边缘对模糊核估计的影响，使得模糊核的估计更加准确。进一步采用超拉普拉斯分布来近似图像梯度的重尾分布，利用

0.5

范数正则化对模糊图像做反卷积，从而恢复出原始图像。与传统方法相比，本文方法可以准确地估计出图像的模糊核，很好地抑制恢复图像的振铃现象，有效地提升遥感图像的质量。模糊图像以及各方法重构图像在同一刀刃下的调制传递函数（MTF）曲线显示，本文方法的MTF曲线得到了较好的提升。

Abstract

On the basis of the degradation process of a blurred image

a convolution fuzzy model and the fuzzy image generation mechanism

a zero-norm regularization kernel estimation method is proposed to overcome the problem that 0 norm is difficult to solve in the remote sensing image reconstruction. By taking a fuzzy nuclear sparse for prior knowledge and corresponding gradient norms for regular items

the method avoids the impact of small edges of the image on blurred kernel and accurately estimates the blur kernel by the blurring image. Furthermore

the super Laplace distribution is used to approximate the heavy-tailed distribution of image gradient

and the norm regularization is taken to deconvolute the blurred image to recover the original image. As compared with the traditional methods

the proposed method estimates the obscure kernel of the image correctly

restrains the ringing phenomena well and improves the quality of remoter sensing image. The experiments for the same blade shows that Modulation Transfer Function(MTF) curve from proposed method is better than those from the blurred images and other reconstructed images.

关键词

Keywords

references

XU L, ZHENG S, JIA J Y. Unnatural l0 sparse representation for natural image deblurring [C]. Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 2013:1107-1114.

王国栋, 徐洁, 潘振宽, 等. 基于归一化超拉普拉斯先验项的运动模糊图像盲复原[J]. 光学精密工程, 2013, 21(5): 1340-1348. WANG G D, XU J, PAN ZH K, et al..Blind image restoration based on normalized hyper laplacian prior term [J]. Opt. Precision Eng., 2013, 21(5): 1340-1348. (in Chinese)

XU Y. Single-Image blind deblurring for non-uniform camera-shake blur [C]. Computer Vision-ACCV 2012, Springer Berlin Heidelberg, 2013:336-348.

XU L, JIA J Y. Depth-aware motion deblurring[C]. 2012 IEEE International Conference on Computational Photography(ICCP),2012:1-8.

赵文达, 赵建, 韩希珍, 等. 基于变分偏微分方程的红外图像增强算法研究[J]. 液晶与显示, 2014, 29(2): 281-285. ZHAO W D, ZHAO J, HAN X ZH, et al.. Infrared image enhancement based on variational partial differential equations [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(2): 281-285. (in Chinese)

CHO S. Registration based non-uniform motion deblurring [J]. Computer Graphics Forum, 2012,31(7):2183-2192.

LUCY L. An iterative technique for the rectification of observed distributions [J]. Astronomical Journal, 1974,76(6):745-754.

WIENER N. Extrapolation, Interpolation, and Smoothing of Stationary Time Series: with Engineering Applications [M]. MIT press, 1964.

KRISHNAN D, R FERGUS. Fast image deconvolution using hyper-Laplacian priors [J]. Advances in Neural Information Processing Systems, 2009, 22:1-9.

李伟红, 董亚莉, 唐述. 多范数混合约束的正则化图像盲复原[J]. 光学精密工程, 2013, 21(5): 1357-1364. LI W H, DONG Y L, TANG SH. Regularized blind image restoration based on multi-norm hybrid constraints [J]. Opt. Precision Eng., 2013, 21(5): 1357-1364. (in Chinese)

FERGUS R. Removing camera shake from a single photograph [J]. ACM Transactions on Graphics (TOG), 2006,25(3):787-794.

XU L, JIA J Y. Two-phase kernel estimation for robust motion deblurring [C]. Computer Vision-ECCV 2010, 2010:157-170.

董雪, 林志贤, 郭太良. 基于LoG算子改进的自适应阈值小波去噪算法[J]. 液晶与显示, 2014, 29(2): 275-280. DONG X, LIN ZH X, GUO T L. Improved self-adaptive threshold wavelet denoising analysis based on LoG operator [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(2): 275-280. (in Chinese)

CHO S, S LEE. Fast motion deblurring [J]. ACM Transactions on Graphics (TOG), 2009,28(5):145.

KRISHNAN D, T TAY, R FERGUS. Blind deconvolution using a normalized sparsity measure [C]. 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011:233-240.

GOLDSTEIM A, FATTAL R. Blur-kernel estimation from spectral irregularities [C]. European Conference on Computer Vision(ECCV),2012:622-635.

郭汉洲, 吕恒毅, 曲利新. 遥感相机动态调制传递函数与时间延迟积分CCD行周期误差的关系[J]. 光学精密工程, 2013,21(8): 2195-2200. GUO H ZH, LU H Y, QU L X. Relation of line transfer period error and dynamic MTF of TDICCD in remote sensing camera [J]. Opt. Precision Eng., 2013, 21(8): 2195-2200. (in Chinese)

Views

229

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimization for optical remote sensing imaging system based on space-invariant image restoration

Estimation of PSF of image system using modified SVD method

Spatial adaptation and frequency fusion network for single remote sensing image super-resolution

Generate adversarial network for super-resolution reconstruction of remote sensing images by fusing edge enhancement and non-local modules

Fast extraction of buildings from remote sensing images by fusion of CNN and Transformer

Related Author

ZHI Xi-yang

ZHANG Wei

HOU Qing-yu

SUN Xuan

WANG Yuan-yuan

SUN Zhi-Min

CAI Zheng

YANG Yichuan

Related Institution

Research Center for Space Optical Engineering, Harbin Institute of Technology

Department of Electron Engineering, Fudan University

Key Laboratory of Optoelectronic Technology and System， Ministry of Education， Chongqing University

Beijing Institute of Space Machinery and Electronics

College of Measurement and Control Technology and Communication Engineering， Harbin University of Science and Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰