Open AccessA Novel Unsupervised Approach for Land Classification Based on Touzi Scattering Vector Model in the Context of Very High Resolution PolSAR Imagery
Author(s) -
Sheng Yih Sun,
Jianhua Gong,
Zhijia Xu
Publication year - 2020
Publication title -
electronics/elektronika
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.128
H-Index - 10
eISSN - 2831-0128
pISSN - 1450-5843
DOI - 10.7251/els2024057g
Subject(s) - wishart distribution , synthetic aperture radar , decomposition , computer science , artificial intelligence , context (archaeology) , remote sensing , radar imaging , invariant (physics) , high resolution , radar , pattern recognition (psychology) , data mining , mathematics , machine learning , geography , ecology , telecommunications , archaeology , multivariate statistics , mathematical physics , biology
With the popularization of very high resolution polarimetric ll-invariant decomposition solution, is employed to extract the scattering properties of different land covers. The parameters of Touzi decomposition act as input dataset for initial classification. A novel classifying algorithm is put forward by means of integrating the Touzi decomposition with conventional Wishart statistical models. Quantitative experiments are then conducted using uninhabited aerial vehicle synthetic aperture radar sample data for evaluating the performance of this new proposed approach. It can be concluded from the experimental results that the new proposed method is superior to the classical method in terms of producer accuracy, user accuracy, and overall accuracy.