Multi-feature extraction method based on Gaussian pyramid and weighted voting for hyperspectral image classification

In this paper, a multi-scale feature extraction and classification method for hyperspectral images(HSI) based on Gaussian pyramid and weighted voting is proposed. Specifically, first, the HSI is decomposed into several Gaussian pyramids to extract multi-scale features, and then the matrix of spectral angle distance (mSAD) is used to generate weight coefficients to evaluate each feature. Finally, the weighted voting is used to obtain the final classification result. By integrating multiple features, the classification accuracy is significantly improved. The superiority of the proposed method is proved by experiments.