A Novel Multi-Feature Joint Learning Method for Fast Polarimetric SAR Terrain Classification

Abstract

Polarimetric synthetic aperture radar (PolSAR) image classification is one of the most important study areas for PolSAR image processing. Many kinds of PolSAR features can be extracted for PolSAR image classification, such as the scattering, polarimetric or image features. However, it is difficult to improve the classification accuracy of PolSAR images by using all these low-level features directly, since they may conflict with each other for classification. Hence, how to joint learn these lowlevel features to obtain high-level discriminating features is a challenging task. To solve this problem, a novel fast multi-feature joint learning method(fMF-JLC) is proposed for PolSAR image classification. The proposed method extract three kinds of low-level features of PolSAR data at first. Then, a multifeature joint sparse representation model(MF-JSR) is proposed by designing joint sparse constraints on the extracted features above. Moreover, the joint sparse features are further compressed to overcome the dimension curse and acquire semantic features by the topic model. By this way, the low-level features are fused and discriminating high-level features are acquired. However, the pixel-wise feature learning method is time consuming. To speed the proposed method, a superpixel-based fast learning method is designed by involving the contextual relationship. Experiments are taken on three sets of real PolSAR data with different sensors and bands, and several compared methods are used to verify the effectiveness of the proposed method. The experimental results illustrate that the proposed method can obtain better performance than the state-ofart methods, especially for the heterogenous areas. INDEX TERMS Polarimetric SAR classification, joint multi-feature sparse representation, joint multifeature learning, fast classification method.

SAR4LCZ-Net: A Complex-Valued Convolutional Neural Network for Local Climate Zones Classification Using Gaofen-3 Quad-Pol SAR Data

“…In order to reduce the speckle on quad-pol SAR images, the coherency matrix is filtered by a sequential approach [35]. Combination of features extracted from scattering matrix and coherency matrix in quad-pol SAR data have been verified effective for terrain classification [27], [36]. We also assemble polarimetric features and spatial features as input features for SAR4LCZ-Net.…”

Polarimetric Synthetic Aperture Radar Image Classification Based on Double-Channel Convolution Network and Edge-Preserving Markov Random Field

“…These features include Cloude decomposition, Freeman decomposition, and Yamaguki decomposition. The detailed feature extraction process can be found in [45], as shown in Table 1. The feature vector is defined as F = { f 1 , f 2 , .…”

Riemannian Nearest-Regularized Subspace Classification for Polarimetric SAR images

“…However, the three compared methods can hardly obtain good performance with only T matrix by the Euclidean distance. Here, we add 53 features including the T vector [17] (shorted by "3F+T" features) as the inputs of the three compared methods. While only the T matrix(shorted by "only T" feature) is used as the input of the proposed RNRS method.…”

“…Recently, representation-based classification methods have been demonstrated to be an effective tool in the field of radar image processing [3]. Representation classification methods can be mainly concluded into three categories: sparse representation classification(SRC) [4], collaborative representation classifier(CRC) [5] and nearest regularization subspace(NRS) Junfei Shi was with the Department of Computer Science and Technology, Shaanxi Key Laboratory for Network Computing and Security Technology, Xi'an University of Technology, Xi'an, China.…”