Semi-supervised PolSAR image classification based on self-training and superpixels

Yangyang Li*, Ruoting Xing, Licheng Jiao, Yanqiao Chen, Yingte Chai, Naresh Marturi, Ronghua Shang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)


Polarimetric synthetic aperture radar (PolSAR) image classification is a recent technology with great practical value in the field of remote sensing. However, due to the time-consuming and labor-intensive data collection, there are few labeled datasets available. Furthermore, most available state-of-the-art classification methods heavily suffer from the speckle noise. To solve these problems, in this paper, a novel semi-supervised algorithm based on self-training and superpixels is proposed. First, the Pauli-RGB image is over-segmented into superpixels to obtain a large number of homogeneous areas. Then, features that can mitigate the effects of the speckle noise are obtained using spatial weighting in the same superpixel. Next, the training set is expanded iteratively utilizing a semi-supervised unlabeled sample selection strategy that elaborately makes use of spatial relations provided by superpixels. In addition, a stacked sparse auto-encoder is self-trained using the expanded training set to obtain classification results. Experiments on two typical PolSAR datasets verified its capability of suppressing the speckle noise and showed excellent classification performance with limited labeled data.

Original languageEnglish
Article number1933
JournalRemote Sensing
Issue number16
Publication statusPublished - 2019

Bibliographical note

Publisher Copyright:
© 2019 by the authors.

Copyright 2019 Elsevier B.V., All rights reserved.


  • Image classification
  • Polarimetric synthetic aperture radar (PolSAR)
  • Self-training
  • Semi-supervised classification
  • Superpixels

ASJC Scopus subject areas

  • General Earth and Planetary Sciences


Dive into the research topics of 'Semi-supervised PolSAR image classification based on self-training and superpixels'. Together they form a unique fingerprint.

Cite this