Many scholars have conducted a number of studies on classifying PolSAR images by the semi-supervised classification algorithm.
Therefore, this study focuses mainly on the issue of hardness when selecting training samples and low classification accuracy in SAR images; research for the classification scheme, which is similar to the semi-supervised algorithm carried out on PolSAR images; and a new classification scheme proposed by combining the improved adaptive region growing algorithm with the Wishart maximum likelihood classification algorithm.
Semi-supervised learning follows the state of PolSAR image classification.
Experiments on data analysis and unsupervised classification with AIRSAR and E-SAR L-band PolSAR images demonstrate the effectiveness of the proposed method.
To illustrate the type of mixed scattering mechanisms, we select an region from AIRSAR L-band PolSAR image over San Francisco.
In this section, we investigated the performance of the proposed scattering mechanism identification scheme on real PolSAR data.
data, the three unique elements of the scattering matrix can be defined as a complex vector
Problem This paper addresses the problem of extracting BAs from high-resolution PolSAR imagery.
Thus, it is of great interest to develop effective and applicable features to extract BAs from high-resolution PolSAR imagery, which describe not only the local pixel-level information but also context information of objects.
9] applied several advanced SAR image processing methods for detection and classification of urban structures with airborne PolSAR data.
This section formulates the PolSAR tomography problem in the CS framework, and investigates the choice of the mixed norm involved in the CS inversion technique.
In this paper, we propose a mixed norm sparse reconstruction method for jointly processing multibaseline PolSAR data and propose a window based iterative algorithm for signal leakage suppression.