The emergence of convolutional neural network (CNN) has greatly promoted the development of hyperspectral image (HSI) classification technology. However, the acquisition of HSI is difficult. Lack of training samples is the primary cause of low classification performance. Traditional CNN-based methods mainly use 2D CNN for feature extraction, which make interband correlations of HSIs underutilized. 3D CNN extracts the joint-spectral-spatial information representation, but it depends on a more complex model. Also, too deep or too shallow network cannot extract the image features well. To tackle these issues, we propose an HSI classification method based on 2D-3D CNN and multi-branch feature fusion. We first combine 2D CNN and 3D CNN to extract image features. Then, by means of the multi-branch neural network, three kinds of features from shallow to deep are extracted and fused in the spectral dimension. Finally, the fused features are passed into several fully connected layers and a softmax layer to obtain the classification results. In addition, our network model utilizes the state-of-the-art activation function Mish to further improve the classification performance. Our experimental results, conducted on four widely used HSI data sets, indicate that the proposed method achieves better performance than the existing alternatives.
Deep-learning methods, especially convolutional neural networks (CNN), have become the first choice for hyperspectral image (HSI) classification to date. It is a common procedure that small cubes are cropped from hyperspectral images and then fed into CNNs. However, standard CNNs find it difficult to extract discriminative spectral–spatial features. How to obtain finer spectral–spatial features to improve the classification performance is now a hot topic of research. In this regard, the attention mechanism, which has achieved excellent performance in other computer vision, holds the exciting prospect. In this paper, we propose a double-branch network consisting of a novel convolution named pyramidal convolution (PyConv) and an iterative attention mechanism. Each branch concentrates on exploiting spectral or spatial features with different PyConvs, supplemented by the attention module for refining the feature map. Experimental results demonstrate that our model can yield competitive performance compared to other state-of-the-art models.
As the Hyperspectral (HS) images usually have low spatial resolution, hyperspectral image (HSI) super-resolution has recently attracted more and more attention to enhance the spatial resolution of HSIs. A common method is to fuse the low-resolution (LR) HSI with a multispectral image (MSI) whose spatial resolution is higher than the HSI. In this paper, we proposed a novel adaptive non-negative sparse representation (ANSR) based model to fuse an HSI and its corresponding MSI. First, basing the linear spectral unmixing, the non-negative structured sparse representation model estimates the sparse codes of the desired high-resolution (HR) HSI from both the LR-HSI and the MSI. Then, the adaptive sparse representation (ASR) can balance the relationship between the sparsity and collaboration by generating a suitable coefficient. Finally, in order to obtain more accurate results, we alternately optimize the spectral basis and coefficients rather than keeping the spectral basis fixed. Alternating direction method of multipliers is applied to solve the proposed optimization problem. Experimental results on both ground-based hyperspectral images and real remote sensing HSIs show the superiority of our proposed approach to some other state-of-the-art HSI super-resolution methods.
Deep learning (DL) has recently been a core ingredient in modern computer vision tasks, triggering a wave of revolutions in various fields. The hyperspectral image (HSI) classification task is no exception. A wide range of DL-based methods have shone brilliantly in HSI classification. However, understanding how to better exploit spectral and spatial information regarding HSI is still an open area of enquiry. In this article, we propose a hybrid convolution and hybrid resolution network with double attention for HSI classification. First, densely connected 3D convolutional layers are employed to extract preliminary spatial–spectral features. Second, these coarse features are fed to the hybrid resolution module, which mines the features at multiple scales to obtain high-level semantic information and low-level local information. Finally, we introduce a novel attention mechanism for further feature adjustment and refinement. Extensive experiments are conducted to evaluate our model in a holistic manner. Compared to several popular methods, our approach yields promising results for four datasets.
In this paper, we present an efficient retrieval algorithm for encrypted speech based on an inverse fast Fourier transform and measurement matrix. Our approach improves query performance, as well as retrieval efficiency and accuracy, compared to existing content-based encrypted speech retrieval methods. Our proposed algorithm constructs a perceptual hash scheme using perceptual hash sequences from original speech files. By classifying the sequences and applying run-length compression, we decrease the cloud storage required for the hash index. We secure the speech database by encrypting it with Henon chaos scrambling, which offers excellent resistance to attacks. Experimental results show that the robustness, discrimination, and feature extraction efficiency of our proposed method are better than the existing alternatives, with good recall and precision ratios and with high retrieval efficiency and accuracy.
Recently, hyperspectral image (HSI) classification has become a popular research direction in remote sensing. The emergence of convolutional neural networks (CNNs) has greatly promoted the development of this field and demonstrated excellent classification performance. However, due to the particularity of HSIs, redundant information and limited samples pose huge challenges for extracting strong discriminative features. In addition, addressing how to fully mine the internal correlation of the data or features based on the existing model is also crucial in improving classification performance. To overcome the above limitations, this work presents a strong feature extraction neural network with an attention mechanism. Firstly, the original HSI is weighted by means of the hybrid spectral–spatial attention mechanism. Then, the data are input into a spectral feature extraction branch and a spatial feature extraction branch, composed of multiscale feature extraction modules and weak dense feature extraction modules, to extract high-level semantic features. These two features are compressed and fused using the global average pooling and concat approaches. Finally, the classification results are obtained by using two fully connected layers and one Softmax layer. A performance comparison shows the enhanced classification performance of the proposed model compared to the current state of the art on three public datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.