• Home
  • Search
  • Eigenvalue Statistical Components-Based PU-Learning for PolSAR Built-Up Areas Extraction and Cross-Domain Analysis
  • Cite Icon13
  • https://doi.org/10.1109/jstars.2020.3000743Copy DOI Icon

Eigenvalue Statistical Components-Based PU-Learning for PolSAR Built-Up Areas Extraction and Cross-Domain Analysis

  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Polarimetric synthetic aperture radar (PolSAR) provides important support for the built-up areas (BA) information analysis, due to the ability of weather-independent imaging and sensitivity to targets scattering and geometric characteristics. However, PolSAR BA with large orientation angles is usually misdetected as vegetation, and labeled BA samples with special orientations are difficult to obtain. Furthermore, the labeled BA samples and trained models can hardly work well in the cross-domain PolSAR imagery BA analysis. This article presents a PolSAR BA extraction method based on eigenvalue statistical components (ESC) and PU-Learning (PUL), and it helps to realize cross-domain BA extraction by combining subspace alignment (SA). First, the roll invariance of coherency-matrix eigenvalues and building orientation effects are analyzed. Then, by adopting the eigenvalue-Wishart unsupervised classification, regional statistical information and rotation-invariant property are comprehensively utilized in ESC. Finally, the BA can be extracted by combining a PUL classifier with only positive samples at the same distinguishable orientation. Combined with SA, the novel ESC-PUL-SA domain adaptation facilitates a robust unsupervised cross-domain PolSAR BA analysis, reducing the differences caused by sensors and imaging scenes. The ESC-PUL BA extraction on seven PolSAR imageries showed that the accuracies reach 92%–98% with only a few positive samples (less than 0.65%). The ESC-PUL-SA performance was further validated by 14 unsupervised cross-domain BA analysis units among 10 datasets, including Radarsat-2, Gaofen-3, AirSAR, and UAVSAR images. With randomly selected positive samples from the source domain, the proposed ESC-PUL-SA achieved accuracies of all cross-domain BA extraction range from 89.64% to 95.53%.

Loading PDF

Similar Papers
  • Research Article
  • Citations25

Extraction of Built-up Areas From Fully Polarimetric SAR Imagery Via PU Learning

  • Apr 01, 2014
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Wen Yang +4
  • PDF
  • Research Article
  • Citations45

Built-up Area Extraction from PolSAR Imagery with Model-Based Decomposition and Polarimetric Coherence

  • Aug 22, 2016
  • Remote Sensing
  • Deliang Xiang +4
  • Conference Article
  • Citations3

Built-Up Areas Extraction from Polsar Imagery Via Eigenvalue Statistical Information and Pu-Learning

  • Jul 01, 2019
  • Rong Gui +5
  • Research Article
  • Citations27

Statistical Scattering Component-Based Subspace Alignment for Unsupervised Cross-Domain PolSAR Image Classification

  • Jul 01, 2021
  • IEEE Transactions on Geoscience and Remote Sensing
  • Rong Gui +4
  • Research Article
  • Citations53

Damage assessment in urban areas using post-earthquake airborne PolSAR imagery

  • Nov 15, 2013
  • International Journal of Remote Sensing
  • Lingli Zhao +5
  • Research Article
  • Citations86

Fisher Linear Discriminant Analysis of coherency matrix for wetland classification using PolSAR imagery

  • Jan 03, 2018
  • Remote Sensing of Environment
  • Masoud Mahdianpari +6
  • Research Article
  • Citations33

A General Feature Paradigm for Unsupervised Cross-Domain PolSAR Image Classification

  • Apr 29, 2021
  • IEEE Geoscience and Remote Sensing Letters
  • Rong Gui +5
  • Conference Article
  • Citations4

Urban area extraction from Polarimetric SAR imagery using only positive samples

  • Oct 01, 2010
  • Ying Liu +3
  • Research Article
  • Citations14

Assessment of the Potential of H/A/Alpha Decomposition for Polarimetric Interferometric SAR Data

  • Apr 01, 2018
  • IEEE Transactions on Geoscience and Remote Sensing
  • Maryam Salehi +2
  • Research Article
  • Citations64

PolSAR Image Classification Based on Deep Convolutional Neural Networks Using Wavelet Transformation

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Ali Jamali +4
  • Research Article
  • Citations18

Feature selection and weighted SVM classifier-based ship detection in PolSAR imagery

  • Sep 02, 2013
  • International Journal of Remote Sensing
  • Xiangwei Xing +3
  • Research Article
  • Citations34

Fusion of polarimetric and texture information for urban building extraction from fully polarimetric SAR imagery

  • Nov 04, 2015
  • Remote Sensing Letters
  • Wei Zhai +3
  • Research Article
  • Citations2

A General Framework for CFAR Detection in PolSAR Imagery Based on Quadratic Statistics

  • Jan 01, 2025
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Ziyuan Yang +5
  • Research Article
  • Citations14

Optical images-based edge detection in Synthetic Aperture Radar images

  • Aug 01, 2015
  • Knowledge-Based Systems
  • Gilberto P Silva +5
  • Research Article
  • Citations86

Ship Detection From PolSAR Imagery Using the Complete Polarimetric Covariance Difference Matrix

  • May 01, 2019
  • IEEE Transactions on Geoscience and Remote Sensing
  • Tao Zhang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.