Title :
Pol-SAR image classification using eigenvalue-based joint statistical framework
Author :
Gou, S.P. ; Wang, W.F. ; Jiao, L.C. ; Wang, S. ; Zhang, X.R.
Author_Institution :
Key Lab. of Intell. Perception & Image Understanding of Minist. of Educ. of China, Xidian Univ., Xi´an, China
Abstract :
In this paper, a novel method based on joint statistical framework is proposed for classification of polarimetric SAR image. The Gaussian model of the maximum eigenvalue and volume scattering power for coherency matrix is estimated to describe their statistical distribution. And Bayesian classifier is used to classify the polarimetric SAR image. In order to make full use of the local context structure of image, the local statistical model is used based on the maximum posterior probability (MAP) rule. The method is tested with the NASA/JPL AIRSAR data.
Keywords :
geophysical image processing; geophysical techniques; image classification; radar polarimetry; remote sensing by radar; synthetic aperture radar; Bayesian classifier; Eigenvalue-BASED JOINT STATISTICAL FRAMEWORK; Gaussian model; MAP rule; NASA-JPL AIRSAR data; POL-SAR image classification; coherency matrix; maximum eigenvalue; maximum posterior probability; polarimetric SAR image classification; volume scattering power; Accuracy; Bayes methods; Eigenvalues and eigenfunctions; Joints; Mathematical model; Scattering; Synthetic aperture radar; Bayesian classifier; Gaussian model; POL-SAR; eigenvalue; volume scattering power;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International
Conference_Location :
Quebec City, QC
DOI :
10.1109/IGARSS.2014.6947060
