When Pixels Team up: Spatially Weighted Sparse Coding for Hyperspectral Image Classification

• Published in: IEEE geoscience and remote sensing letters 2015-01, Vol.12 (1), p.107-111
• Main Authors: Soltani-Farani, Ali, Rabiee, Hamid R.
• Format: Article
• Language: English
• Subjects: Accuracy; Classification; Dictionaries; dictionary learning; Digital video; Encoding; hyperspectral imagery (HSI); Hyperspectral imaging; linear support vector machines (SVMs); reweighed ell_{1}; Support vector machines; Training data
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2014.2328319

In this letter, a spatially weighted sparse unmixing approach is proposed as a front-end for hyperspectral image classification using a linear SVM. The idea is to partition the pixels of a hyperspectral image into a number of disjoint spatial neighborhoods. Since neighboring pixels are often composed of similar materials, their sparse codes are encouraged to have similar sparsity patterns. This is accomplished by means of a reweighted ℓ 1 framework where it is assumed that fractional abundances of neighboring pixels are distributed according to a common Laplacian Scale Mixture (LSM) prior with a shared scale parameter. This shared parameter determines which endmembers contribute to the group of pixels. Experiments on the AVIRIS Indian Pines show that the model is very effective in finding discriminative representations for HSI pixels, especially when the training data is limited.