An IR Strong Clutter Background Suppression Algorithm Based on Sparse Kernel Method

ZHU Bin; FAN Xiang; CHENG Zheng-dong; WANG Di; FANG Yi-qiang; CHEN Xiao-si

doi:10.3969/j.issn.0372-2112.2015.04.013

您当前的位置：

首页 >

文章列表页 >

An IR Strong Clutter Background Suppression Algorithm Based on Sparse Kernel Method

更新时间：2025-07-16

- An IR Strong Clutter Background Suppression Algorithm Based on Sparse Kernel Method
- Acta Electronica Sinica Vol. 43, Issue 4, Pages: 716-721(2015)
- 作者机构：
  
  1. 脉冲功率激光技术国家重点实验室,安徽,合肥,230037
  2. 电子工程学院光电系,安徽,合肥,230037
  3. 脉冲功率激光技术国家重点实验室,安徽,合肥,230037
  4. 电子工程学院光电系,安徽,合肥,230037
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61307025);Natural Science Foundation of Anhui Province (No.1308085QF122)
- DOI：10.3969/j.issn.0372-2112.2015.04.013
  CLC： TN911.73
- Published：2015
- 稿件说明：
移动端阅览
ZHU Bin, FAN Xiang, CHENG Zheng-dong, et al. An IR Strong Clutter Background Suppression Algorithm Based on Sparse Kernel Method[J]. Acta Electronica Sinica, 2015, 43(4): 716-721.
DOI：

ZHU Bin, FAN Xiang, CHENG Zheng-dong, et al. An IR Strong Clutter Background Suppression Algorithm Based on Sparse Kernel Method[J]. Acta Electronica Sinica, 2015, 43(4): 716-721. DOI： 10.3969/j.issn.0372-2112.2015.04.013.

摘要

杂波背景抑制一直是红外弱小目标检测面临的难题.背景抑制可分为背景预测和差分滤波两步.针对强杂波背景呈现非线性分布的特征

提出了一种基于稀疏化核递推最小二乘(KRLS)算法的非线性背景抑制算法.算法采用监督学习模型

使用序列图像作为训练样本.通过稀疏化控制学习函数的复杂度并剔除冗余信息

不但可以提高学习机器的推广能力

还可以降低运算量.使用真实红外图像对算法进行了测试

并分析了算法参数.实验结果表明:算法可自适应预测不同类型的强杂波背景

并有效抑制背景杂波.

Abstract

Clutter background suppression is always a difficulty of infrared (IR) dim and point target detection.Background suppression is divided into background estimation and difference filtering.Aiming at the nonlinear distribution of strong clutter background

a spares kernel recursive least squares (KRLS) based nonlinear background suppression algorithm is proposed.This method uses sequence images as training sample in supervised learning model.The complexity of learned function is controlled

and the redundant information is discarded by sparsification.In this way

the generalization of learning machine can be enhanced;moreover

the computational burden can be reduced.In the experiments

real IR images are used to test the algorithm

and the parameters are analyzed.Experimental results show that different kinds of strong clutter background can be estimated

and then be suppressed.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fast Orthogonal Kernel Matching Pursuit Based on Greedier Strategy

Expression Recognition Based on Sparse Selection and PLDA

Related Author

FU Li-hua

LI Hong-wei

ZHANG Meng

ZHANG Rui

JIANG Chen-zhi

SU Jian-bo

Related Institution

School of Mathematics and Physics, China University of Geosciences

Department of Computer, Central China Normal University

School of Mathematics and Physics China University of Geosciences Wuhan Hubei China

Department of Computer Central China Normal University Wuhan Hubei China

Ministry of Education Key Laboratory of System Control and Information Processing, Department of Automation, Shanghai Jiao Tong University

⁰