Polarmetric SAR images classification based on sparse representation theory

Abstract

Feature extraction and image classification using PolSAR images is currently of great interest in SAR applications. On the basis of the sparse characteristics of the features for PolSAR image classification, a supervised PolSAR image classification method based on sparse representation is proposed in this paper, in which the test data can be firstly projected onto a subset of training vectors from the dictionary, then the residual errors with respect to each atom are evaluated and considered as the criteria for classification, and the ultimate class results can be obtained according to the atom with the least residual error. In addition, a Simplified Matching Pursuit (SMP) algorithm is proposed to solve the optimization problem of sparse representation of PolSAR images. The experimental results of Danish EMISAR L-band fully polarimetric SAR data of Foulum Area (DK) confirm our method outputs an excellent result and moreover the classification process is simpler and less time consuming.

A Novel Deep Fully Convolutional Network for PolSAR Image Classification

“…Polarimetric synthetic aperture radar (PolSAR), which can utilize SAR complex images in different polarimetric channels to recognize the orientation, geometric shape, configuration and composition of targets [1], has become one of the most advanced technologies [2]. In the past decades, a large amount of PolSAR data has been acquired as a series of PolSAR systems are put into use [3].…”

“…Therefore, for PolSAR image classification, the neighborhood of a pixel is set as the input to get the class of the pixel [38][39][40][41][42][43]. For instance, recording one pixel in the image as p 1 , the neighborhood of p 1 is set as the input to get the class of p 1 . Therefore, for one pixel (recorded as p 2 ) in the neighborhood of p 1 , p 1 will also be involved in the process of getting the class of p 2 .…”