Convolutional neural networks (CNNs) have exhibited extraordinary achievements in hyperspectral image (HSI) classification due to their detailed representation of features. However, the improvement of classification accuracy often leads to an evident increase in the complexity of the model, which makes it challenging for the model with the state-of-the-art performance to be applied in the actual scene. Considering MobileNetV3 as a lightweight feature extractor, this article proposes a model suitable for HSI classification based on MobileNetV3. To decrease the problem of massive redundant calculations in the existing spatial attention module, this article proposes a more concise and efficient spatial attention module based on the visual feature maps experiment. Besides, multiclass focal-loss is applied to solve the problem that the difficulty of classification varies for each sample. The experimental results demonstrate that in the case of using very few training sets, the proposed model can tremendously reduce the number of calculations and parameters while maintaining high accuracy.

Hyperspectral image (HSI) classification is one of the basic tasks of remote sensing image processing, which is to predict the label of each HSI pixel. Convolution neural network (CNN) and graph convolution neural network (GCN) have become the current research focus due to their outstanding performance in the field of HSI classification in recent years. However, GCN is a transductive learning method, which needs all nodes to participate in the training process to get the node embedding. Graph sample and aggregation (GraphSAGE) is an important branch of graph neural network, which can flexibly aggregate new neighbor nodes in non-Euclidean data of any structure, and capture long-range contextual relationships. Superpixel-based GraphSAGE can not only integrate the global spatial relationship of data, but also further reduce its computing cost. CNN can extract pixel-level features in a small area, and our center attention module (CAM) and center weighted convolution (CW-Conv) can also improve the feature extraction ability of CNN by enhancing the dominant position of target pixels. In order to make full use of the advantages of CNN and GraphSAGE, we propose a center weighted convolution and GraphSAGE (CW-SAGE) cooperative network for HSI classification. Specifically, graph simple and aggregate branch is constructed by superpixel-based encoder and decoder modules, then pixel-level features are extracted by a central attention convolutional neural network. Finally, the features of the two branches are spliced together for feature fusion. We conduct experiments on three hyperspectral datasets and compare the results with other current state-of-the-art methods. A series of experiments demonstrate the advantages of our method.

Spectral emissivity is an essential and sensitive parameter to characterize the radiative capacity of the solid surface in scientific and engineering applications, which would be non-negligibly affected by surface morphology. However, there is a lack of assessment of the effect of roughness on emissivity and a straightforward method for estimating the emissivity of rough surfaces. This paper established an estimating method based on constructing random rough surfaces to predict rough surface (Geometric region) emissivity for metal solids. Based on this method, the emissivity of ideal gray and non-gray body surfaces was calculated and analyzed. The calculated and measured spectral emissivities of GH3044, K465, DD6, and TC4 alloys with different roughness were compared. The results show that the emissivity increases with the roughness degree, and the enhancement effect weakens with the increase of roughness or emissivity due to the existing limit (emissivity ε = 1.0). At the same time, the roughness would not change the overall spectral distribution characteristics but may attenuate the local features of the spectral emissivity. The estimated results are in good agreement with the experimental data for the above alloys’ rough surfaces. This study provides a new reliable approach to obtaining the spectral emissivity of rough surfaces. This approach is especially beneficial for measuring objects in extreme environments where emissivity is difficult to obtain. Meanwhile, this study promotes an understanding of surface morphology’s effect mechanism on emissivity.