A New Algorithm of Target Classification Based on Maximum and Minimum Polarizations

Author

Yang, Wang ; Jiaguo, Lu ; Changyao, Zhang

Author_Institution

Key Lab. of Intelligent Comput. & Signal Process. of Minist. of Educ., Anhui Univ., Hefei

fYear

2006

fDate

16-19 Oct. 2006

Firstpage

1

Lastpage

4

Abstract

The polarization signature of a given pixel in a radar image represents scattering mechanisms from various scattering elements. This paper presents an analysis of maximum and minimum polarizations of five kinds of polarization signatures: co-polarized, cross-polarized, completely polarized, completely unpolarized, and total available power signatures. We propose a new algorithm of target classification based on these maximum and minimum polarizations, then, conduct the experiment on the measured polarimetric SAR data. Experimental results show that this algorithm is robust to pixel-by-pixel target classification in radar images

Keywords

electromagnetic wave polarisation; electromagnetic wave scattering; image classification; radar imaging; radar polarimetry; synthetic aperture radar; maximum polarization; measured polarimetric SAR data; minimum polarization; polarization signature; radar image; target classification; Classification algorithms; Polarization; Radar imaging; Radar polarimetry; Radar remote sensing; Radar scattering; Radar signal processing; Signal processing algorithms; Surface waves; Wavelength measurement; maximum and minimum polarizations; polarimetric SAR; polarization signatures; target decomposition;

fLanguage

English

Publisher

ieee

Conference_Titel

Radar, 2006. CIE '06. International Conference on

Conference_Location

Shanghai

Print_ISBN

0-7803-9582-4

Electronic_ISBN

0-7803-9583-2

Type

conf

DOI

10.1109/ICR.2006.343544

Filename

4148503