Terrain classification of Pol-SAR based on dilated convolution and polarization decomposition

ZHANG Ze-yu; LIU Chang

Chinese

您当前的位置：

首页 >

文章列表页 >

Terrain classification of Pol-SAR based on dilated convolution and polarization decomposition

更新时间：2026-09-04

- Terrain classification of Pol-SAR based on dilated convolution and polarization decomposition
- Vol. 37, Issue 12, Pages: 70-76(2020)
- 作者机构：
  
  1. 中国科学院机构空天信息创新研究院,北京,100094
  2. 中国科学院大学机构,北京,101408
  3. 中国科学院电子学研究所,北京,100190
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2020
- 稿件说明：
移动端阅览
张泽宇, 刘畅. 基于极化分解和膨胀卷积的极化SAR地物分类[J]. 微电子学与计算机, 2020, 37(12): 70-76.

ZHANG Ze-yu, LIU Chang. Terrain classification of Pol-SAR based on dilated convolution and polarization decomposition[J]. 2020, 37(12): 70-76.
张泽宇, 刘畅. 基于极化分解和膨胀卷积的极化SAR地物分类[J]. 微电子学与计算机, 2020, 37(12): 70-76. DOI：

ZHANG Ze-yu, LIU Chang. Terrain classification of Pol-SAR based on dilated convolution and polarization decomposition[J]. 2020, 37(12): 70-76. DOI：

摘要

针对基于深度学习的极化SAR地物分类中存在的标注数据少且未能利用SAR极化分解特征的问题

提出了一种基于极化分解和膨胀卷积的极化SAR地物分类方法.在低采样率下训练基于像素分类的卷积神经网络(CNN)

将其卷积层参数迁移到同结构的膨胀卷积网络(DCNN)

解决了膨胀卷积网络训练数据不足的问题; 然后将反应地物散射特性的极化分解特征与包含高维空间语义信息的膨胀卷积特征图进行联合

使用联合特征构建随机森林(RF)进行分类.实验表明

特征图和极化分解的联合特征能够实现更为精确的分类

且由于引入膨胀卷积和随机森林

算法具有很高的实时性.

Abstract

In order to solve the problems of the lack of labeling data and the failure to make use of the polarization decomposition feature of SAR in Pol-SAR terrain classification methods based on deep learning

a polarimetric SAR terrain classification method based on dilated convolution and polarization decomposition is proposed. The convolutional neural network (CNN) based on pixel classification was trained at low sampling rate

and its convolutional layer parameters were transferred to the expansive convolutional network (DCNN) with the same structure

thus solving the problem of insufficient training data of the expansive convolutional network. Then the polarization decomposition feature reflecting the scattering characteristics of ground objects is combined with the expansive convolution feature map containing the high-dimensional spatial semantic information

and the random forest (RF) is constructed by using the joint feature for classification. Experiments show that the alliance of polarization decomposition features and feature maps can achieve more accurate classification

and the algorithm has high real-time performance due to the dilated convolution and random forest.

关键词

Keywords

references

ZHANG Z, WANG H, XU F, et al. Complex-valued convolutional neural network and its application in polarimetric SAR image classification[J].IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(12):7177-7188. DOI: 7177

YE D, LI Z, WANG Y J. Research on behavior recognition method based on SPLDA dimensionality reduction and XGBoost classifier[J].Microelectronics % Computer, 2019, 36(6):35-39. DOI: 35

SHEN Y L, SONG J, WAN Z C. SVM feature selection and parameter optimization based on improved firework algorithm[J].Microelectronics % Computer, 2018, 35(1):21-25. DOI: 21

VAN B S, COMBER A, LAMB A. Random forest classification of salt marsh vegetation habitats using quad-polarimetric airborne SAR, elevation and optical RS data[J].Remote Sensing of Environment, 2014, 149:118-129. DOI: 118

CHEN S W, TAO C S. PolSAR image classification using polarimetric-feature-driven deep convolutional neural network[J].IEEE Geoscience and Remote Sensing Letters, 2018, 15(4):627-631. DOI: 627

GU Y F. Research on semantic segmentation algorithm based on grouped dilated convolution and cascade network[D]. Harbin: Harbin Institute of Technology, 2018.

YE Q W, WU X F. Design of objective loss function to suppress inefficient learning in end-to-end deep image segmentation network[J].Microelectronics % Computer, 2019, 36(9):38-43. DOI: 38

YAMAGUCHI Y, MORIYAMA T, ISHIDO M, et al. Four-component scatteriSng model for polarimetric SAR image decomposition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(8):1699-1706. DOI: 1699

ZHANG J Q. Research on polarization SAR ground object classification based on deep learning[D].Beijing : Chinese academy of surveying and mapping, 2018.

DENG Y, ZHANG H, WANG C, et al. Object-oriented polarization SAR water extraction method combining texture and polarization decomposition[J].Remote sensing technology and application, 2016, 31(4):714-723. DOI: 714

FREEMAN A, DURDEN S L. A three-component scattering model for polarimetric SAR data[J].IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(3):963-973. DOI: 963

KROGAGER E. New decomposition of the radar target scattering matrix[J].IET Electronics Letters, 1990, 26(18):1525-1526. DOI: 1525

DONG J. Statistical analysis of polarization SAR image features and research on classification algorithm[D].Wuhan : Wuhan University, 2018.

LI C L, TIE Y, QI L. Multi-feature speech emotion recognition based on random forest classification optimization[J].Microelectronics % Computer, 2019, 36(1):70-73. DOI: 70

ZHANG L, ZOU B, ZHANG J, et al. Classification of polarimetric SAR image based on support vector machine using multiple-component scattering model and texture features[J].EURASIP Journal on Advances in Signal Processing, 2009, 2010:1-9. DOI: 1

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Road extraction based on SAR polarization characteristics and SVM

Research on assembly action recognition based on MSS-YOLO-MPHands fusion architecture

A review of large model development: technological evolution from BERT to Deepseek

Monte carlo analysis of V-layout trench SiC neutron detector

A feature-oriented context understanding and slice analysis network for tuberculosis detection

Related Author

SU Xiaojie

LIU Xiuqing

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
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