Supervised Polarimetric SAR Image Classification Using Tensor Local Discriminant Embedding

Abstract

Feature extraction is a very important step for polarimetric synthetic aperture radar (PolSAR) image classification. Many dimensionality reduction (DR) methods have been employed to extract features for supervised PolSAR image classification. However, these DR-based feature extraction methods only consider each single pixel independently and thus fail to take into account the spatial relationship of the neighboring pixels, so their performance may not be satisfactory. To address this issue, we introduce a novel tensor local discriminant embedding (TLDE) method for feature extraction for supervised PolSAR image classification. The proposed method combines the spatial and polarimetric information of each pixel by characterizing the pixel with the patch centered at this pixel. Then each pixel is represented as a third-order tensor, of which the first two modes indicate the spatial information of the patch (i.e. the row and the column of the patch) and the third mode denotes the polarimetric information of the patch. Based on the label information of samples and the redundance of the spatial and polarimetric information, a supervised tensor-based dimensionality reduction technique, called TLDE, is introduced to find three projections which project each pixel, that is, the third-order tensor into the low-dimensional feature. Finally, classification is completed based on the extracted features using the nearest neighbor (NN) classifier and the support vector machine (SVM) classifier. The proposed method is evaluated on two real PolSAR data sets and the simulated PolSAR data sets with various number of looks. The experimental results demonstrate that the proposed method not only improves the classification accuracy greatly, but also alleviates the influence of speckle noise on classification.

PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features

“…Not all the compared methods used every data set utilized in our work, thus, the compared methods are not exactly the same for each data set. The compared approaches include classical algorithms, such as SVM [15], Wishart [16] and Mean shift [54], pixel-wised algorithms [21,51] and region-based algorithms [37,55,56]. Method in [21] applied two cascaded convolutional layers to learn hierarchical polarimetric spatial features for PolSAR image classification.…”

“…Method in [37] combined SRCs with superpixels to classify PolSAR images. Method proposed in [51] adopted the nearest neighbor and SVM classifiers to classify PolSAR images based on the features extracted by tensor local discriminant embedding method. Method in [55] utilized Fuzzy superpixels to assist PolSAR image classification.…”

“…The second data set named San Francisco is the four-look L-band PolSAR image with size 900 × 1024 pixels, which can be downloaded from https://earth.esa.int/web/polsarpro/data-sources/ sample-datasets. It includes 4 categories: sea, mountains, grass and buildings [51]. The Pauli color code image and its ground truth are shown in Figure 5.…”

Cluster-Based Tensorial Semisupervised Discriminant Analysis for Feature Extraction of SAR Images

“…Therefore, tensor-based methods have been proposed because they can preserve the overall spatial structure, and they have been applied in several areas, including biological [21] and medical research [22], facial recognition [23], [24], natural image processing [25], hyperspectral image analysis [26]- [28], [42] and PolSAR image processing [29], [30]. Lower rank tensor approximation (LTRA) [26] is an extension of PCA to higher-order data sets that assumes strong global correlations in the spatial and feature domains.…”

The Generalized Gamma-DBN for High-Resolution SAR Image Classification

“…Because they can organize better weights of deep learning structure, these methods reduce the computational complexity of network training and retain the spatial structure of remote sensing images effectively. However, some of tensor-based approaches [26] may over-smooth part of line-type and point-type targets, such as boulevards and bridges, due to the fact that the patches charactering of these pixels. All of these works report a better classification or recognition accuracies due to the fact that deep networks can extract effective features compared with the other methods.…”