Polarimetric synthetic aperture radar (PolSAR) images contain useful information, which can lead to extensive land cover interpretation and a variety of output products. In contrast to optical imagery, there are several challenges in extracting beneficial features from PolSAR data. Deep learning (DL) methods can provide solutions to address PolSAR feature extraction challenges. The convolutional neural networks (CNNs) and graph convolutional networks (GCNs) can drive PolSAR image characteristics by deploying kernel abilities in considering neighborhood (local) information and graphs in considering long-range similarities. A novel dual-branch fusion of CNN and mini-GCN is proposed in this study for PolSAR image classification. To fully utilize the PolSAR image capacity, different spatial-based and polarimetric-based features are incorporated into CNN and mini-GCN branches of the proposed model. The performance of the proposed method is verified by comparing the classification results to multiple state-of-the-art approaches on the airborne synthetic aperture radar (AIRSAR) dataset of Flevoland and San Francisco. The proposed approach showed 1.3% and 2.7% improvements in overall accuracy compared to conventional methods with these AIRSAR datasets. Meanwhile, it enhanced its one-branch version by 0.73% and 1.82%. Analyses over Flevoland data further indicated the effectiveness of the dual-branch model using varied training sampling ratios, leading to a promising overall accuracy of 99.9% with a 10% sampling ratio.

/pdf/dual-branch-fusion-of-convolutional-neural-network-and-graph-3oa29zbl.pdf

Dual-Branch Fusion of Convolutional Neural Network and Graph Convolutional Network for PolSAR Image Classification

The effectiveness of a classifier is dependent on how accurately it classify the boundary samples. To enhance the discrimination between the boundary pixels, in this research we propose a novel feature extraction technique that generates a profile of the polarimetric synthetic aperture radar (PolSAR)image by using Jensen Shannon Divergence (JSD). The experiment conducted on two real PolSAR data sets using support vector machines (SVM) classifier shows the potentiality of the proposed profile. For both the data sets, the proposed profile provides at least 3% improvement in the classification accuracy as compared to the traditional T3db features. 

Classification of Polarimetric SAR Image using JS-Divergence Profile

The effectiveness of a classifier is dependent on how accurately it classify the boundary samples. To enhance the discrimination between the boundary pixels, in this research we propose a novel feature extraction technique that generates a profile of the polarimetric synthetic aperture radar (PolSAR)image by using Jensen Shannon Divergence (JSD). The experiment conducted on two real PolSAR data sets using support vector machines (SVM) classifier shows the potentiality of the proposed profile. For both the data sets, the proposed profile provides at least 3% improvement in the classification accuracy as compared to the traditional T3db features.

ABSTRACT Classification of polarimetric SAR images into different ground covers has important applications in fields such as land mapping, agriculture monitoring, and assessment. The Wishart supervised classifier is one of the most widely used and general purpose classifier for polarimetric SAR data. However, it is a pixel-based classifier, so the performance is greatly affected by inherent speckle noise. The impact of speckle noise can be reduced by considering the spatial information from neighbouring pixels for classification tasks. In this paper, we aim to improve classification results by incorporating spatial-contextual information along with preservation of significant details such as edges and micro-regions. For this purpose, a conditional random field (CRF) based model is proposed for polarimetric SAR data along with Wishart and Wishart mixture model (WMM) classifiers, namely Wishart-CRF and WMM-CRF, to perform the classification. The model is compared with the Markov random field (MRF) based model as well as neural network-based models. The results are analysed in terms of accuracy and preservation of details such as edges and micro-regions. The model is assessed using three full polarimetric SAR benchmark data sets. The CRF model exhibits better classification results by significantly reducing the noise and preserving the finer details of edges and small regions.

Nilam Chaudhari

Papers

Edge-Preserving classification of polarimetric SAR images using Wishart distribution and conditional random field