Depth Feature Extraction for Hyperspectral Image Small Sample Classification

The problem of insufficient labeled samples has restricted the application of deep learning method in hyperspectral image (HSI) classification tasks. Fusion of remote sensing images from different sources such as HSI and LiDAR is a common strategy to improve the classification accuracy. However, obtaining multisource registered remote sensing images of the same area is time-consuming, which limits the application of multisource strategy in practice. Motivated by the recent success of large models in different fields, we propose to extract depth information from large models and fuse it with HSIs to improve the small sample classification accuracy. Specifically, we use the pretrained foundation large model to estimate the depth information of HSIs as the depth features, and then input the original spectral features and depth features into the support vector machine (SVM) to complete the classification. In order to further improve the classification accuracy, we propose to use the sliding window method to extract the depth features of different bands, so as to obtain more rich depth features. A large number of classification experiments on six benchmark datasets verify the effectiveness of the proposed method.