A Fast and Accurate Despeckling Method with Optimized Nonlinear Diffusion

ZHENG Shi-chao; FENG Wen-sen; NIU Jian-wei

doi:10.3969/j.issn.0372-2112.2017.12.001

您当前的位置：

首页 >

文章列表页 >

A Fast and Accurate Despeckling Method with Optimized Nonlinear Diffusion

更新时间：2025-07-16

- A Fast and Accurate Despeckling Method with Optimized Nonlinear Diffusion
- Acta Electronica Sinica Vol. 45, Issue 12, Pages: 2825-2831(2017)
- 作者机构：
  
  1. 北京航空航天大学计算机学院虚拟现实技术与系统国家重点实验室,北京,100191
  2. 北京科技大学自动化学院,北京,100083
  3. 北京航空航天大学计算机学院虚拟现实技术与系统国家重点实验室,北京,100191
  4. 北京科技大学自动化学院,北京,100083
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2017.12.001
  CLC： TP751.1
- Published Online：25 December 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
ZHENG Shi-chao, FENG Wen-sen, NIU Jian-wei. A Fast and Accurate Despeckling Method with Optimized Nonlinear Diffusion[J]. Acta Electronica Sinica, 2017, 45(12): 2825-2831.
DOI：

ZHENG Shi-chao, FENG Wen-sen, NIU Jian-wei. A Fast and Accurate Despeckling Method with Optimized Nonlinear Diffusion[J]. Acta Electronica Sinica, 2017, 45(12): 2825-2831. DOI： 10.3969/j.issn.0372-2112.2017.12.001.

摘要

合成孔径雷达（Synthetic Aperture Radar，SAR）图像相干斑去噪一直以来都是SAR图像处理的一项关键技术.本文提出一种基于最优非线性扩散的快速相干斑抑制算法，该算法使用最近提出的基于可训练非线性扩散的图像复原框架，并针对合成孔径雷达强度图像，结合相干斑噪声的统计特性，训练非线性扩散过程中的滤波器参数和响应函数参数.实验结果表明，该算法性能与PPBit、SAR-BM3D等主流相干斑去噪算法性能相当甚至更优；同时与这些算法相比，该算法计算效率能够提高75%以上，并且适于并行运算实现.

Abstract

SAR (Synthetic Aperture Radar) despeckling is one of the key technologies in SAR image processing.This paper proposes an efficient despeckling algorithm based on optimized nonlinear diffusion model

which exploits the trainable nonlinear reaction diffusion framework.For the despeckling task

we train the parameters of linear filters and the influence functions

taking into account the speckle noise statistics of the intensity SAR image.Experimental results show that the proposed method provides comparable or even better results in comparison with PPBit and SAR-BM3D.Meanwhile

our proposed model is of high computation efficiency

and is well-suited for parallel computation.

关键词

Keywords

references

Views

501

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Quantification Method of Convolutional Neural Network Based on Data Standard Deviation

HAN: Hotspot-Aware Attention Enhanced News Recommendation

Feature-Space Optimization-Inspired and Self-Attention Enhanced Neural Network Reconstruction Algorithm for Image Compressive Sensing

Single Image Super-Resolution Reconstruction Using Deep Residual Networks with Non-decimated Wavelet Edge Learning

Research and Challenges of Medical Image Landmark Detection Based on Deep Learning

Related Author

HUANG Yun

ZHANG Fan

GUO Wei

YANG Guang

CHEN Li

DING Qi

TIAN Xuan

SUN Guo-dong

Related Institution

Henan Administration of Radio and Television Monitoring Center，， Hennan

National Digital Switching System Engineering Technology Research Center，， Hennan

Information Engineering University，， Hennan

Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration

School of Information Science and Technology, Beijing Forestry University

⁰