Multi-scale Tensor l1-Based Algorithm for Hyperspectral Image Classification

Sparsity-based model has been successfully applied in hyper spectral image classification. However, previous ℓ₁-based method fails to consider the spatial structure of each pixel. In this paper, we generalize the ℓ₁-based method to its tensor form, which takes full advantage of the spatial structure of the pixel. To optimize the scale of the spatial structure, a multi-scale fusion framework based on the ensemble learning method is proposed to further improve classification performance. Experimental results demonstrate that our proposed method can achieve state-of-the-art classification performance.