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.

In this paper, a new target classification algorithm based on adaptive local aspect dictionary pair learning for synthetic aperture radar (SAR) images is developed. To that end, first, the aspect sector of one testing sample is determined adaptively by a regularized non-negative sparse learning method. Second, a synthesis dictionary and an analysis dictionary are jointly learned from the corresponding training subset located in the aspect sector. By doing so, the local aspect dictionary pair is obtained. Finally, the class label of the testing sample is inferred by a use of the minimum reconstruction residual under the representation with the local aspect dictionary pair. Using the local aspect sector training subset rather than the global aspect training set reduces the interference of a large amount of unrelated training samples, which leads to a more discriminative local aspect dictionary pair for target classification. The experiments are conducted with the Moving and Stationary Target Acquisition and Recognition (MSTAR) database, and the results demonstrate that the proposed approach is effective and superior to the state-of-the-art methods.