A New Scheme of Unsupervised Terrain Classification for POLSAR Imagery Based on Target Scattering Similarities

CHEN Qiang; JIANG Yong-mei; LU Jun; KUANG Gang-yao

您当前的位置：

首页 >

文章列表页 >

A New Scheme of Unsupervised Terrain Classification for POLSAR Imagery Based on Target Scattering Similarities

更新时间：2025-07-16

- A New Scheme of Unsupervised Terrain Classification for POLSAR Imagery Based on Target Scattering Similarities
- Acta Electronica Sinica Vol. 38, Issue 12, Pages: 2729-2734(2010)
- 作者机构：
  
  国防科学技术大学电子科学与工程学院,湖南,长沙,410073
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN957
- Published：2010
- 稿件说明：
移动端阅览
CHEN Qiang, JIANG Yong-mei, LU Jun, et al. A New Scheme of Unsupervised Terrain Classification for POLSAR Imagery Based on Target Scattering Similarities[J]. Acta Electronica Sinica, 2010, 38(12): 2729-2734.
DOI：

CHEN Qiang, JIANG Yong-mei, LU Jun, et al. A New Scheme of Unsupervised Terrain Classification for POLSAR Imagery Based on Target Scattering Similarities[J]. Acta Electronica Sinica, 2010, 38(12): 2729-2734. DOI：

摘要

针对H-Alpha散射分类存在的不足

本文提出了一种基于目标散射相似性的POLSAR图像地物散射分类新方案.该方案首先利用散射随机性将地物分为高散射随机性、中散射随机性和低散射随机性三类

然后根据散射相似性参数对这三类进一步细分.由于该方案根据散射相似性参数自动确定散射类别

克服了采用Alpha人工确定散射类别的不足;散射相似性参数计算简便

克服了H-Alpha散射分类运算量偏大的不足.作为一种实际应用

在新方案框架下

本文给出了一种基于球面散射、偶次散射和体散射相似性参数

以及散射随机性的度量参数——极化散射熵的散射分类新方法.该方法在利用极化散射熵将地物分为三类基础上

根据三个散射相似性参数进一步将地物分为十类.由于这三种典型散射对应实际地物散射

该方法的十种散射类别能很好地描述实际地物情况.实测极化数据的实验结果

验证了新方案的可行性和新方法的有效性.

Abstract

Aiming at the deficiency of the H-Alpha based classification

a new scheme of unsupervised terrain classification is proposed based on target scattering similarities.This new scheme divides terrain scattering into three classes with target scattering randomness firstly;and then subdivides these three classes with target scattering similarities ulteriorly.As terrain scattering class is determined by target scattering similarities automatically

the deficiency of the arbitrarily fixed linear decision boundaries of Alpha angle is overcomed.As an application

a new method of unsupervised terrain classification is also presented under the frame of the new scheme.After the partition of terrain scattering with target entropy which is a measure of target scattering randomness

the new method subdivides three classes into ten classes with surface scattering similarity

double scattering similarity and volume scattering similarity ulteriorly.As surface scattering

double scattering and volume scattering are the inherent characteristics of terrain physical scattering mechanisms

the classification result of the new method is consistent with the real terrain scattering.With the real polarimetric data of San Francisco

the feasibility of the new scheme and the validity of the new method are validated.

关键词

Keywords

references

Views

1204

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A New Scattering-Identification Based Unsupervised Terrain Classification for POLSAR Image

The SAR Image Terrain Classification Algorithm Combining Quadratic Gamma Discrimination Classifier and Beta-Prime Statistic Model

The High-Resolution SAR Image Terrain Classification Algorithm Based on Mixed Double Hint Layers RBFN Model

Related Author

CHEN Qiang

JIANG Yong-mei

LU Jun

KUANG Gang-yao

FU Kun

SUN Zhen-zhen

WU Yi-rong

SUN Zhen-zhen

Related Institution

School of Electronic Science and Engineering,National University of Defense Technology

Institute of Electronics,Chinese Academy of Sciences

Beijing Institute of System Engineering

Institute of Electronics Chinese Academy of Sciences Beijing China

Beijing Institute of System Engineering Beijing China

⁰