Classification of Tree Types by Polarimetric Pi-SAR

Motoyuki Sato, Takafumi Koike

Research output: Contribution to conferencePaperpeer-review

6 Citations (Scopus)

Abstract

In order to classify tree types, we introduce a new technique, which detects the change of Polarimetric Entropy parameters. We define the difference of the two-dimensional polarimetric entropy parameters, and applied the proposed technique to Pi-SAR airborne polarimetric SAR data. The result in an urban area shows that the seasonal change is very random and we could not find significant changes between two scenes. Then, we applied the technique to a forested region. The change in coniferous trees and broad leafed trees is statistically different. Using the change in polarimetric entropy properties, we find this technique can be used for tree type classification.

Original languageEnglish
Pages431-433
Number of pages3
Publication statusPublished - 2003 Nov 24
Event2003 IEEE IGARSS: Learning From Earth's Shapes and Colours - Toulouse, France
Duration: 2003 Jul 212003 Jul 25

Other

Other2003 IEEE IGARSS: Learning From Earth's Shapes and Colours
CountryFrance
CityToulouse
Period03/7/2103/7/25

Keywords

  • Pi-SAR
  • Polarimetri Entropy
  • Radar Polrainmtry
  • Tree Classification

ASJC Scopus subject areas

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Fingerprint Dive into the research topics of 'Classification of Tree Types by Polarimetric Pi-SAR'. Together they form a unique fingerprint.

Cite this