Convolutional neural network (CNN) has been successfully introduced to hyperspectral image (HSI) classification and achieved effective performance. With the depth of the CNN increases, it may cause the gradient to become zero, and the structure lacks the utilization of the correlated spatial feature information between different convolutional layers. At the same time, this single-scale convolution kernel is insufficient in expressing the complex spatial structure information of HSI. Additionally, the CNN-based methods treat the HSIs spectral band data as a disordered vector in the process of feature extraction, which abandons the exploitation of its internal spectral correlations. To address these issues, we propose a novel spectral-spatial network classification framework based on multiscale dense connected convolutional network (DenseNet) and bi-direction recurrent neural network (Bi-RNN) with attention mechanism network (MDRN). For the proposed MDRN, in terms of spatial feature extraction, a multi-scale DenseNet is exploited to combine shallow and deep convolution features to extract the multi-scale and complex spatial structure features at each layer. In the aspects of spectral feature extraction, Bi-RNN with attention mechanism is used to capture the inner spectral correlations within a continuous spectrum. Three standard real hyperspectral datasets were used to verify the effectiveness of the proposed MDRN approach. Experimental results indicate that the proposed MDRN method can make full use of the spectral and spatial information of the image, and it has better performance than some advanced algorithms in HSI classification. Finally, in the application of hyperspectral data captured by Gaofen-5 (GF-5) satellite, the practicability of the proposed MDRN method is also superior to other methods.

No abstract

Traditional convolutional neural networks (CNNs) can be applied to obtain the spectral-spatial feature information from hyperspectral images (HSIs). However, they often introduce significant redundant spatial feature information. The octave convolution network is frequently utilized instead of traditional CNN to decrease spatial redundant information of the network and extend its receptive field. However, the 3D octave convolution-based approaches may introduce extensive parameters and complicate the network. To solve these issues, we propose a new HSI classification approach with a multi-scale spectral-spatial network-based framework that combines 2D octave and 3D CNNs. Our method, called MOCNN, first utilizes 2D octave convolution and 3D DenseNet branch networks with various convolutional kernel sizes to obtain complex spatial contextual feature information and spectral characteristics, separately. Moreover, the channel and the spectral attention mechanisms are, respectively, applied to these two branch networks to emphasize significant feature regions and certain important spectral bands that comprise discriminative information for the categorization. Furthermore, a sample balancing strategy is applied to address the sample imbalance problem. Expansive experiments are undertaken on four HSI datasets, demonstrating that our MOCNN approach outperforms several other methods for HSI classification, especially in scenarios dominated by limited and imbalanced sample data.

Sparse unmixing plays a crucial role in the field of hyperspectral image unmixing technology, leveraging the availability of pre-existing endmember spectral libraries. In recent years, there has been a growing trend in incorporating spatial information from hyperspectral images into sparse unmixing models. There is a strong spatial correlation between pixels in hyperspectral images (that is, the spatial information is very rich), and many sparse unmixing algorithms take advantage of this to improve the sparse unmixing effect. Since hyperspectral images are susceptible to noise, the feature separability of ground objects is reduced, which makes most sparse unmixing methods and models face the risk of degradation or even failure. To address this challenge, a novel robust dual spatial weighted sparse unmixing algorithm (RDSWSU) has been proposed for hyperspectral image unmixing. This algorithm effectively utilizes the spatial information present in the hyperspectral images to mitigate the impact of noise during the unmixing process. For the proposed RDSWSU algorithm, which is based on ℓ1 sparse unmixing framework, a pre-calculated superpixel spatial weighting factor is used to smooth the noise, so as to maintain the original spatial structure of hyperspectral images. The RDSWSU algorithm, which builds upon the ℓ1 sparse unmixing framework, employs a pre-calculated spatial weighting factor at the superpixel level. This factor aids in noise smoothing and helps preserve the inherent spatial structure of hyperspectral images throughout the unmixing process. Additionally, another spatial weighting factor is utilized in the RDSWSU algorithm to capture the local smoothness of abundance maps at the sub-region level. This factor helps enhance the representation of piecewise smooth variations within different regions of the hyperspectral image. Specifically, the combination of these two spatial weighting factors in the RDSWSU algorithm results in an enhanced sparsity of the abundance matrix. The RDSWSU algorithm, which is a sparse unmixing model, offers an effective solution using the alternating direction method of multiplier (ADMM) with reduced requirements for tuning the regularization parameter. The proposed RDSWSU method outperforms other advanced sparse unmixing algorithms in terms of unmixing performance, as demonstrated by the experimental results on synthetic and real hyperspectral datasets.