Estimating directions of arrival (DOA) without knowledge of the source number is regarded as a challenging task, particularly when coherence among sources exists. Researchers have trained deep learning (DL)-based models to attack the problem of DOA estimation. However, existing DL-based methods for coherent sources do not adapt to variable source numbers or require signal independence. Herein, we put forward a new framework combining parallel DOA estimators with Toeplitz matrix reconstruction to address the problem. Each estimator is constructed by connecting a multi-label classifier to a spatial filter, which is based on convolutional-recurrent neural networks. Spatial filters divide the angle domain into several sectors, so that the following classifiers can extract the arrival directions. Assisted with Toeplitz-based method for source-number determination, pseudo or missed angles classified by the estimators will be reduced. Then, the spatial spectrum can be more accurately recovered. In addition, the proposed method is data-driven, so it is naturally immune to signal coherence. Simulation results demonstrate the predominance of the proposed method and show that the trained model is robust to imperfect circumstances such as limited snapshots, colored Gaussian noise, and array imperfections.
The semantic segmentation of remote sensing images is a significant research direction in digital image processing. The complex background environment, irregular size and shape of objects, and similar appearance of different categories of remote sensing images have brought great challenges to remote sensing image segmentation tasks. Traditional convolutional-neural-network-based models often ignore spatial information in the feature extraction stage and pay less attention to global context information. However, spatial context information is important in complex remote sensing images, which means that the segmentation effect of traditional models needs to be improved. In addition, neural networks with a superior segmentation performance often suffer from the problem of high computational resource consumption. To address the above issues, this paper proposes a combination model of a modified multiscale deformable convolutional neural network (mmsDCNN) and dense conditional random field (DenseCRF). Firstly, we designed a lightweight multiscale deformable convolutional network (mmsDCNN) with a large receptive field to generate a preliminary prediction probability map at each pixel. The output of the mmsDCNN model is a coarse segmentation result map, which has the same size as the input image. In addition, the preliminary segmentation result map contains rich multiscale features. Then, the multi-level DenseCRF model based on the superpixel level and the pixel level is proposed, which can make full use of the context information of the image at different levels and further optimize the rough segmentation result of mmsDCNN. To be specific, we converted the pixel-level preliminary probability map into a superpixel-level predicted probability map according to the simple linear iterative clustering (SILC) algorithm and defined the potential function of the DenseCRF model based on this. Furthermore, we added the pixel-level potential function constraint term to the superpixel-based Gaussian potential function to obtain a combined Gaussian potential function, which enabled our model to consider the features of various scales and prevent poor superpixel segmentation results from affecting the final result. To restore the contour of the object more clearly, we utilized the Sketch token edge detection algorithm to extract the edge contour features of the image and fused them into the potential function of the DenseCRF model. Finally, extensive experiments on the Potsdam and Vaihingen datasets demonstrated that the proposed model exhibited significant advantages compared to the current state-of-the-art models.
The development of convolution neural networks (CNNs) has become a significant means to solve the problem of remote sensing scene image classification. However, well-performing CNNs generally have high complexity and are prone to overfitting. To handle the above problem, we present a new classification approach using an mmsCNN–HMM combined model with stacking ensemble mechanism in this paper. First of all, a modified multi-scale convolution neural network (mmsCNN) is proposed to extract multi-scale structural features, which has a lightweight structure and can avoid high computational complexity. Then, we utilize a hidden Markov model (HMM) to mine the context information of the extracted features of the whole sample image. For different categories of scene images, the corresponding HMM is trained and all the trained HMMs form an HMM group. In addition, our approach is based on a stacking ensemble learning scheme, in which the preliminary predicted values generated by the HMM group are used in an extreme gradient boosting (XGBoost) model to generate the final prediction. This stacking ensemble learning mechanism integrates multiple models to make decisions together, which can effectively prevent overfitting while ensuring accuracy. Finally, the trained XGBoost model conducts the scene category prediction. In this paper, the six most widely used remote sensing scene datasets, UCM, RSSCN, SIRI-WHU, WHU-RS, AID, and NWPU, are selected to carry out all kinds of experiments. The numerical experiments verify that the proposed approach shows more important advantages than the advanced approaches.
In compressed sensing (CS), one seeks to down-sample some high-dimensional signals and recover them accurately by exploiting the sparsity of the signals. However, the traditional sparsity assumption cannot be directly satisfied in most practical applications. Fortunately, many signals-of-interest do at least exhibit a low-complexity representation with respect to a certain transformation. Particularly, total variation (TV) minimization is a notable example when the transformation operator is a difference matrix. Presently, many theoretical properties of total variation have not been completely explored, e.g., how to estimate the precise location of phase transitions and their rigorous understanding is still in its infancy. So far, the performance and robustness of the existing algorithm for phase transition prediction of TV model are not satisfactory. In this paper, we design a new approximate message passing algorithm to solve the above problems, called total variation vector approximate message passing (TV-VAMP) algorithm. To be specific, we first consider the problem from the Bayesian perspective, and formulate it as an optimization problem. Then, the vector factor graph for the TV model is constructed based on the formulized problem. Finally, the TV-VAMP algorithm is derived according to the idea of probabilistic inference in machine learning. Compared with the existing algorithm, our algorithm can be applied to a wider range of measurements distributions, including the non-zero-mean Gaussian distribution measurements matrix and ill-conditioned measurements matrix. Furthermore, in experiments with various settings, including different measurement distribution matrices, signal gradient sparsity, and measurement times, the proposed algorithm can almost reach the target mean squared error (−60 dB) with fewer iterations and better fit the empirical phase transition curve.