An efficient classification method of fully polarimetric SAR image based on polarimetric features and spatial features

Xiaorong Xue, Liping Di, Liying Guo, Li Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Polarimetric SAR(PolSAR) has played more and more important roles in earth observation. Polarimetric SAR image classification is one of the key problems in the PolSAR image interpretation. In this paper, based on the scattering properties of fully polarimetric SAR data, combing the statistical characteristics and neighborhood information, an efficient method of fully polarimetric SAR image classification is proposed. In the method, polarimetric scattering characteristics of fully polarimetric SAR image is used, and in the denoised total power image of polarimetric SAR, Span, the texture features of gray level co-occurrence matrix are extracted at the same time. Finally, the polarimetric information and texture information are combined for fully polarimetric SAR Image classification by clustering algorithm. The experimental results show that better classification results can be obtained in the Radarsat-2 data with the proposed method.

Original languageEnglish
Title of host publication2015 4th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages327-331
Number of pages5
ISBN (Electronic)9781467380874
DOIs
Publication statusPublished - Sept 9 2015
Externally publishedYes
Event4th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2015 - Istanbul, Turkey
Duration: Jul 20 2015Jul 24 2015

Publication series

Name2015 4th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2015

Conference

Conference4th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2015
Country/TerritoryTurkey
CityIstanbul
Period7/20/157/24/15

Keywords

  • gray level co-occurrence matrix
  • image classification
  • polarimetric feature
  • Polarimetric SAR

ASJC Scopus subject areas

  • Earth and Planetary Sciences (miscellaneous)
  • Computers in Earth Sciences

Fingerprint

Dive into the research topics of 'An efficient classification method of fully polarimetric SAR image based on polarimetric features and spatial features'. Together they form a unique fingerprint.

Cite this