Search

Unlike natural images, remote sensing scene images usually contain one scene label and many object labels, and many object labels are arranged dispersedly, which brings great difficulties to feature extraction of scene label. To accurately identify scene labels from remote sensing scene images with multiple object labels, it is important to fully understand the global context of the image. In order to solve the challenges of multi-label scene images and improve the classification performance, a global context feature extraction module is proposed in this paper. The module combines the semantics information of different regions through a global pooling and three different scale sub-regions pooling, which makes the module have stronger ability of global feature representation. In addition, in order to fully understand the semantic content of remote sensing images, a three branch joint feature extraction module is constructed, which consists of the global context feature module, 3 × 3 convolution branch and identity branch are fused. Finally, a lightweight convolution neural network based on joint features (LCNN-JF) is constructed using traditional convolution, depthwise separable convolution, joint feature extraction module and classifier for remote sensing scene image classification. A series of experimental results on four datasets, UCM, AID, RSSCN and NWPU, demonstrate that the proposed method has better feature representation ability and can achieve better classification of remote sensing scene images. [ABSTRACT FROM AUTHOR]

In recent years, convolution neural networks (CNNs) and graph convolution networks (GCNs) have been widely used in hyperspectral image classification (HSIC). CNNs can effectively extract the spatial spectral features of hyperspectral images (HSIs), while GCNs can quickly capture the structural features of HSIs, which makes the effective combination of the two is beneficial to improve classification performance of hyperspectral images. However, the high redundancy of feature information and the problem of small sample are still the major challenges of HSIC. In order to alleviate these problems, in this paper, a new graph and double pyramid attention network based on linear discrimination of spectral interclass slices (GDPA_LDSICS) is proposed. First, a linear discrimination of spectral inter class slices (LDSICS) module is designed. The LDSICS module can effectively eliminate a lot of redundancy in spectral dimension, which is conducive to subsequent feature extraction. Then, the spatial spectral deformation (SSD) module is constructed, which can effectively correlate the spatial spectral information closely. Finally, in order to alleviate the problem of small sample, a double branch structure of CNN and GCN is developed. On the CNN branch, a double pyramid attention (DPA) structure is designed to model context semantics to avoid information loss caused by long-distance feature extraction. On the GCN branch, an adaptive dynamic encoding (ADE) method is proposed, which can more effectively capture the topological structure of spatial spectral features. Experiments on four open datasets show that the GDPA_LDSICS can provide better classification performance and generalization performance than other most advanced methods. [ABSTRACT FROM AUTHOR]

Gabor filter is widely used to extract spatial texture features of hyperspectral images (HSI) for HSI classification; however, a single Gabor filter cannot obtain the complete image features. In the paper, we propose an HSI classification method that combines the Gabor filter (GF) and domain-transformation standard convolution (DTNC) filter. First, we use the Gabor filter to extract spatial texture features from the first two principal components of the dimensionality-reduction HSI with PCA. Second, we use the DTNC filter to extract spatial correlation features from HSI in all bands. Finally, the Large Margin Distribution Machine (LDM) uses the linear fusion of the two kinds of spatial features to classify HSI. The experimental results show that the classification accuracy of Indian Pines, Pavia University, and Kennedy Space Center data sets is 96.64, 98.23, and 98.95% with only 4, 3, and 6% training samples, respectively; and these accuracies are 2–20% higher than the other tested methods. Compared with the hyperspectral information based on SVM, EPF, IFRF, PCA-EPFs, LDM-FL, and GFDN method, the proposed method, GFDTNCLDM, significantly improves the accuracy of HSI classification. [ABSTRACT FROM AUTHOR]