Classification of RISAT-1 hybrid polarimetric data for various land features

Author

Turkar, Varsha ; De, Suvranu ; Ponnurangam, G.G. ; Deo, Rinki ; Rao, Y.S. ; Das, Aruneema

Author_Institution

CSRE, Indian Inst. of Technol. - Bombay, Mumbai, India

fYear

2013

fDate

23-27 Sept. 2013

Firstpage

494

Lastpage

497

Abstract

Mean and standard deviation of backscattering coefficients (σ⁰) of RISAT-1 data acquired over Mumbai in hybrid and linear dual polarizations have been analysed for various land features. Classification accuracy between RISAT-1 hybrid polarimetric data and RADARSAT-2 simulated hybrid polarimetric data has been compared. Wishart supervised and Support Vector Machine (SVM) classifiers are used for this study. It has been observed that the classification accuracy can be improved by using m-d or m-χ decomposition along with Circular Polarization Ratio (CPR) and SPAN of hybrid polarimetric data.

Keywords

learning (artificial intelligence); radar imaging; radar polarimetry; remote sensing by radar; support vector machines; synthetic aperture radar; terrain mapping; India; Mumbai; RADARSAT-2 simulated hybrid polarimetric data; RISAT-1 hybrid polarimetric data classification; SPAN; Wishart supervised classifier; backscattering coefficients; circular polarization ratio; classification accuracy; land features; linear dual polarization; m-chi decomposition; m-delta decomposition; standard deviation; support vector machine classifier; Accuracy; Azimuth; Backscatter; Standards; Support vector machines; Synthetic aperture radar; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Synthetic Aperture Radar (APSAR), 2013 Asia-Pacific Conference on

Conference_Location

Tsukuba

Type

conf

Filename

6705126