PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features

Abstract

Polarimetric synthetic aperture radar (PolSAR) image classification plays an important role in various PolSAR image application. And many pixel-wise, region-based classification methods have been proposed for PolSAR images. However, most of the pixel-wise methods can not model local spatial relationship of pixels due to negative effects of speckle noise, and most of the region-based methods fail to figure out the regions with the similar polarimetric features. Considering that color features can provide good visual expression and perform well for image interpretation, in this work, based on the PolSAR pseudo-color image over Pauli decomposition, we propose a supervised PolSAR image classification approach combining learned superpixels and quaternion convolutional neural network (QCNN). First, the PolSAR RGB pseudo-color image is formed under Pauli decomposition. Second, we train QCNN with quaternion PolSAR data converted by RGB channels to extract deep color features and obtain pixel-wise classification map. QCNN treats color channels as a quaternion matrix excavating the relationship among the color channels effectively and avoiding information loss. Third, pixel affinity network (PAN) is utilized to generate the learned superpixels of PolSAR pseudo-color image. The learned superpixels allow the local information exploitation available in the presence of speckle noise. Finally, we fuse the pixel-wise classification result and superpixels to acquire the ultimate pixel-wise PolSAR image classification map. Experiments on three real PolSAR data sets show that the proposed approach can obtain 96.56%, 95.59%, and 92.55% accuracy for Flevoland, San Francisco and Oberpfaffenhofen data set, respectively. And compared with state-of-the-art PolSAR image classification methods, the proposed algorithm can obtained competitive classification results.

Fuzzy Superpixels Based Semi-Supervised Similarity-Constrained CNN for PolSAR Image Classification

“…The Pauli RGB image, the GT map and the color code are shown in Figure 5. To demonstrate the performance of the FS-SCNN method, we compare FS-SCNN with four state-of-the-art PolSAR classification methods, RV-CNN [27], CV-CNN [21], LS-QCNN [31] and STS [10]. In the process of fuzzy superpixels-based sample sets selection, the sliding window and the step are set to 8 × 8 and 1, respectively.…”

Classification of polarimetric SAR images using compact convolutional neural networks

“…This ground truth with the specified class types exactly corresponds to the GTD used in (Kiranyaz et al 2012;Uhlmann et al 2011;Ince, Ahishali, and Kiranyaz 2017). Similar class definitions are used in many other studies (Liu et al 2018;Zhang et al 2019;Huang et al 2019;Yin, Yang, and Yamaguchi 2009). For SFBay_L, selected regions for train and test are shown in Figure 3.…”

A Novel Unsupervised Classification Method for Sandy Land Using Fully Polarimetric SAR Data

“…Classification algorithms can be categorized as pixel-wise and region-based [26]. Pixelwise algorithms focus on the processing of a single pixel, while neglecting the similarity between adjacent pixels belonging to the same type of target [27].…”

“…Compared with directly using the original image, the amount of data processing is greatly reduced, the problems of insufficient memory and slow processing speed are improved [35]. Furthermore, as for clustering algorithms, such as k-means and expectation maximization (EM), must assume a convex spherical sample space, and they tend to fall into local optima [23][24][25][26]. Fortunately, the spectral clustering algorithm, which is based on graph theory, can transform clustering into a graph partitioning problem.…”