Ground-Based Remote Sensing Cloud Classification via Context Graph Attention Network
ABSTARCT :
Most ground-based remote sensing cloud classification methods focus on learning representation features for cloud images while ignoring the correlations among cloud images. Recently, graph convolutional network (GCN) is applied to provide the correlations for ground-based remote sensing cloud classification, in which the graph convolutional layer aggregates information from the connected nodes of graph in a weighted way. However, the weights assigned by GCN cannot reflect the importance of connected nodes precisely, which declines the discrimination of the aggregated features (AFs). To overcome the limitation, in this article, we propose the context graph attention network (CGAT) for ground-based remote sensing cloud classification. Specifically, the context graph attention layer (CGA layer) of CGAT is proposed to learn the context attention coefficients (CACs) and obtain the AFs of nodes based on the CACs. We compute the CACs not only considering the two connected nodes but also their neighborhood nodes in order to stabilize the aggregation process. In addition, we propose to utilize two different transformation matrices to transform the node and its connected nodes into new feature spaces, which could enhance the discrimination of AFs. We concatenate the AFs with the deep features (DFs) as final representations for cloud classification. Since existing ground-based cloud data sets (GCDs) have limited cloud images, we release a new data set named GCD that is the largest one for ground-based cloud classification. We conduct a series of experiments on GCD, and the experimental results verify the effectiveness of CGAT.
EXISTING SYSTEM :
? Different from objectoriented classification, scene classification is a considerably challenging problem because of the variance and complex spatial distributions of ground objects existing in the scenes.
? Considering the number of scene categories and the accuracy saturation of the existing scene classification data sets.
? These methods all used pre-trained CNNs as feature extractors and then fused or combined the features extracted by existing CNNs.
? Two key factors that influences the performance of scene classification tasks are intraclass diversity and interclass similarity existing in remote sensing images.
DISADVANTAGE :
? Some scholars have attempted to use the GNN to solve visual problems, such as image classification.
? However, due to the accumulation of misclassification information during the generation of label sequences, the use of the RNN may cause an error propagation problem .
? However, due to the difference between image data and graph-structured data, it is still a problem worth exploring to mine the spatio-topological relationship of images via GAT.
? Thus, how to effectively extract discriminative semantic representations to distinguish multiple categories is still an open problem that deserves much more exploration.
PROPOSED SYSTEM :
• A number of advanced scene classification systems or approaches have been proposed, especially driven by deep learning.
• After this, a number of deep learning-based scene classification algorithms were proposed, such as CNN-based methods and GAN-based methods.
• A number of reviews of scene classification approaches have been published.
• Because of fusing features from the space and frequency domains, the proposed method is able to provide more discriminative feature representations.
• After extensive experiments, their proposed framework showed superior classification performance.
ADVANTAGE :
? Benefiting from the nonlinear hierarchical abstract ability of deep learning, the convolutional neural network (CNN) has been extensively exploited to address MLRSSC and shows impressive performance .
? Extensive experimental results on two publicly available MLRSSC datasets, such as UCM multi-label dataset and AID multi-label dataset show that our proposed method can obtain superior performance compared with state-of-the-art methods.
? The superior performances on both UCM and AID multi-label datasets can show the robustness and effectiveness of our method.
? Obviously, the use of multi-head attention can improve the classification performance because it can learn more abundant feature representations.
|