Exploring Structural Consistency in Graph Regularized Joint Spectral-Spatial Sparse Coding for Hyperspectral Image Classification

Abstract

In hyperspectral image classification, both spectral and spatial data distributions are important in describing and identifying different materials and objects in the image. Furthermore, consistent spatial structures across bands can be useful in capturing inherent structural information of objects. These imply that three properties should be considered when reconstructing an image using sparse coding methods. First, the distribution of different ground objects leads to different coding coefficients across the spatial locations. Second, local spatial structures change slightly across bands due to different reflectance properties of various object materials. Finally and more importantly, some sort of structural consistency shall be enforced across bands to reflect the fact that the same object appears at the same spatial location in all bands of an image. Based on these considerations, we propose a novel joint spectral-spatial sparse coding model that explores structural consistency for hyperspectral image classification. For each band image, we adopt a sparse coding step to reconstruct the structures in the band image. This allows different dictionaries be generated to characterize the band-wise image variation. At the same time, we enforce the same coding coefficients at the same spatial location in different bands so as to maintain consistent structures across bands. To further promote the discriminating power of the model, we incorporate a graph Laplacian sparsity constraint into the model to ensure spectral consistency in the dictionary generation step. Experimental results show that the proposed method outperforms some state-of-the-art spectral-spatial sparse coding methods.