Spatial-Aware Dictionary Learning for Hyperspectral Image Classification
This work addresses hyperspectral image classification for remote sensing applications, presenting an incremental improvement by integrating spatial context into dictionary learning.
The paper tackles hyperspectral image classification by developing a structured dictionary-based model that incorporates spectral and contextual characteristics, using joint sparse regularization to enforce common sparsity patterns within spatial neighborhoods, and achieves effective classification results as confirmed by experiments on real hyperspectral images.
This paper presents a structured dictionary-based model for hyperspectral data that incorporates both spectral and contextual characteristics of a spectral sample, with the goal of hyperspectral image classification. The idea is to partition the pixels of a hyperspectral image into a number of spatial neighborhoods called contextual groups and to model each pixel with a linear combination of a few dictionary elements learned from the data. Since pixels inside a contextual group are often made up of the same materials, their linear combinations are constrained to use common elements from the dictionary. To this end, dictionary learning is carried out with a joint sparse regularizer to induce a common sparsity pattern in the sparse coefficients of each contextual group. The sparse coefficients are then used for classification using a linear SVM. Experimental results on a number of real hyperspectral images confirm the effectiveness of the proposed representation for hyperspectral image classification. Moreover, experiments with simulated multispectral data show that the proposed model is capable of finding representations that may effectively be used for classification of multispectral-resolution samples.