Search

Sea ice has a significant effect on climate change and ship navigation. Hence, it is crucial to draw sea-ice maps that reflect the geographical distribution of different types of sea ice. Many automatic sea-ice classification methods using synthetic aperture radar (SAR) images are based on the polarimetric characteristics or image texture features of sea ice. They either require professional knowledge to design the parameters and features or are sensitive to noise and condition changes. Moreover, ice changes over time are often ignored. In this article, we propose a new SAR sea-ice image classification method based on a combined learning of spatial and temporal features, derived from residual convolutional neural networks (ResNet) and long short-term memory (LSTM) networks. In this way, we achieve automatic and refined classification of sea-ice types. First, we construct a seven-type ice data set according to the Canadian Ice Service ice charts. We extract spatial feature vectors of a time series of sea-ice samples using a trained ResNet network. Then, using the feature vectors as inputs, the LSTM network further learns the variation of the set of sea-ice samples with time. Finally, the extracted high-level features are fed into a softmax classifier to output the most recent ice type. Taking both spatial features and time variation into consideration, our method can achieve a high classification accuracy of 95.7% for seven ice types. Our method can automatically produce more objective sea-ice interpretation maps, allowing detailed sea-ice distribution and improving the efficiency of sea-ice monitoring tasks. [ABSTRACT FROM AUTHOR]

Deep learning (DL) methods usually need to collect a large amount of labeled data to extract deep features. However, due to the difficulty of obtaining numerous labeled data from synthetic aperture radar (SAR) images, unsupervised feature learning has been focused on SAR image processing. In this article, we propose a 3-D sparse model (3-DSM) to extract deep sparse features from SAR images in an unsupervised way. Concretely, 3-DSM learns the convolution kernels by minimizing the error between the features and the constructed sparse maps, without labeled samples. Thus, the discriminative features can be extracted in an unsupervised way by the learned convolution kernels and are able to capture the main structural information of SAR images. Furthermore, to the best of our knowledge, 3-DSM first specifies the sparsity of convolution kernels, with each convolution kernel exhibiting its independence from the others and the redundancy of convolution kernels being diminishing. It means that each convolution kernel extracts its unique structural features of SAR images. Consequently, in the feature extraction, 3-D sparsities have been specified, including width, height, and depth, with the acquisition of discriminative less-redundant features. The effectiveness of 3-DSM is demonstrated by the feature extraction and segmentation of the simulated and real SAR images. [ABSTRACT FROM AUTHOR]

In order to more efficiently mine the features of polarimetric synthetic aperture radar (PolSAR) and establish a more appropriate classification model, this article proposes an improved convolutional autoencoder (ICAE) based on texture feature fusion (TFF-ICAE) for PolSAR terrain classification. First, TFF-ICAE specifically designs a multi-indicator squeeze-and-excitation (MI-SE) block and incorporates it into the CAE network. MI-SE can enhance the essential feature information while suppressing the interference information as much as possible, and it can effectively increase the between-class distance while reducing the within-class distance. Then, TFF-ICAE uses gray level co-occurrence matrix (GLCM) to capture the texture features, and it optimally fuses these texture features and the deep features extracted by ICAE to complete the multilevel feature fusion, elevating the feature representation completeness of the terrain. That is, TFF-ICAE effectively enhances the feature separation capability of different categories while greatly elevating the feature representation completeness. Experiments on the datasets of San Francisco, Oberpfaffenhofen, and Flevoland show that the proposed TFF-ICAE, respectively, achieves overall accuracies of 93.44%, 97.61%, and 97.78%, which are at least 0.92%, 1.52%, and 0.97% higher than other algorithms. Undoubtedly, the superiority of TFF-ICAE is verified on these datasets. [ABSTRACT FROM AUTHOR]

The complementarity of synthetic aperture radar (SAR) and optical images allows remote sensing observations to “see” unprecedented discoveries. Image matching plays a fundamental role in the fusion and application of SAR and optical images. However, both the geometric imaging pattern and the physical radiation mechanism of these two sensors are significantly different, so that the images show complex geometric distortion and nonlinear radiation differences. This phenomenon brings great challenges to image matching, which neither the handcrafted descriptors nor the deep learning-based methods have adequately addressed. In this article, a novel image-based matching method for SAR to optical images via an image-based convolutional network with spatial pyramid aggregated pooling (SPAP) and an attention mechanism is proposed, namely MAP-Net. The original image is embedded through the convolutional neural network to generate the feature map. Through the information extraction and abstraction of the original imagery, the embedded features containing the high-level semantic information are more robust to the geometric distortion and radiation variation among the different modal images, which is beneficial to the matching of cross-modal images. The adoption of the SPAP module makes the network more capable of integrating global and local contextual information. The attention block weights the dense features generated from the network to extract the key features that are invariant, distinguishable, repeatable, and suitable for the image matching task. In the experiments, five sets of multisource and multiresolution SAR and optical images with wide and varied ground coverage were used to evaluate the accuracy of MAP-Net, compared to both handcrafted and deep learning-based methods. The experimental results show that the MAP-Net method is superior to the current state-of-the-art image matching methods for SAR to optical images. [ABSTRACT FROM AUTHOR]

Building segmentation of synthetic aperture radar (SAR) images is a challenging task that has not been solved well. High-resolution interferometric SAR (InSAR) images can provide delicate textures and interferometric phase images useful for building segmentation. However, current semantic segmentation networks in computer vision cannot be directly applied in InSAR building segmentation tasks to get good results because of the InSAR images’ particularity. In this article, we present a novel complex-valued convolutional and multifeature fusion network (CVCMFF Net) specifically for building semantic segmentation of InSAR images. This CVCMFF Net not only learns from the complex-valued SAR images but also considers multiscale and multichannel feature fusion. It can effectively segment the layover, shadow, and background on both the simulated InSAR building images and the real airborne InSAR images. The segmentation performance of CVCMFF Net is significantly improved compared with those of other state-of-the-art networks. By feature visualization, the feature extraction rule and feature fusion mechanism of the network are explored. We hope that the proposed network can be beneficial to InSAR phase filtering, phase unwrapping, and information extraction in urban areas. [ABSTRACT FROM AUTHOR]

With the increased number of synthetic aperture radar (SAR) systems that have been launched in recent years, many high-quality images have been produced for precise earth observation. The number of available images requires new feature extraction techniques to capture enough discriminant information from high-resolution SAR images. To effectively characterize different land covers, a multiscale local Fisher pattern (MLFP) is proposed to extract both statistical and spatial properties in this work. First, the Fisher vector (FV) of each pixel is calculated after the statistical distribution of high-resolution SAR intensities is modeled via a Gamma mixture model. Then, the generative and discriminant information implied in the FV is exploited after the extraction of the geometrical information between neighboring pixels within different scales. Two experiments are conducted to demonstrate the performance of the proposed MLFP, which are high-resolution SAR image land-cover classification and SAR scene classification. Compared with some existing approaches, the proposed MLFP shows superior performance after the statistical and spatial structure information from different land covers is exploited. [ABSTRACT FROM AUTHOR]

In this article, we propose a fast superpixel region merging algorithm for synthetic aperture radar (SAR) image segmentation. With our previously proposed adaptive superpixel generation approach (ALFCE), an initial over-segmentation superpixel map for SAR imagery can be obtained. A sketch edge map is used here to eliminate the mixed superpixels to refine the over-segmentation. Then, we focus on rapid superpixel merging for efficient and accurate SAR image segmentation by using the statistical region merging (SRM) framework. This article proposes a new merging order with the consideration of statistical dissimilarity measure and common boundary length penalty, as well as the homogeneity constraint for each superpixel pair. For the merging predicate, we define an adaptive merging threshold according to the image complexity, making the proposed superpixel merging no need to set any merging parameters in advance. Disjoint set is utilized in this article to map the superpixel pairs to pixel pairs for the sake of fast region merging, which has a low computation cost even with the increasing of superpixels. Experimental results on synthetic and real SAR images demonstrate that the segmentation precision of our proposed method can reach more than 85% and also superior to other state-of-the-art methods in terms of computational efficiency. [ABSTRACT FROM AUTHOR]